Tootfinder

Rachel Tashjian, most recently the fashion critic for The Washington Post, joins CNN as a senior style reporter for a new digital product (Brian Steinberg/Variety)
https://variety.com/2025/tv/news/cnn-rachel-tashjian-fashion-critic-washington-p…

CNN Hire Washington Post Fashioin Critic Rachel Tashjian
CNN hires Rachel Tashjian, who has been fashion critic at The Washington Post, as the Warner Bros. Discovery outlet seeks new digital presence

'Even MAGA people smell it': Critic says Trump moves show he 'thinks his base is stupid' - Alternet.org
https://www.alternet.org/msn-uk/trump-jeffrey-epstein-guilty/

Comparative Analysis of Parameterized Action Actor-Critic Reinforcement Learning Algorithms for Web Search Match Plan Generation
Ubayd Bapoo, Clement N Nyirenda
https://arxiv.org/abs/2510.03064

Comparative Analysis of Parameterized Action Actor-Critic Reinforcement Learning Algorithms for Web Search Match Plan Generation
This study evaluates the performance of Soft Actor Critic (SAC), Greedy Actor Critic (GAC), and Truncated Quantile Critics (TQC) in high-dimensional decision-making tasks using fully observable environments. The focus is on parametrized action (PA) spaces, eliminating the need for recurrent networks, with benchmarks Platform-v0 and Goal-v0 testing discrete actions linked to continuous action-parameter spaces. Hyperparameter optimization was performed with Microsoft NNI, ensuring reproducibility…

Certainty-Guided Reasoning in Large Language Models: A Dynamic Thinking Budget Approach
Jo\~ao Paulo Nogueira, Wentao Sun, Alonso Silva, Laith Zumot
https://arxiv.org/abs/2509.07820

Certainty-Guided Reasoning in Large Language Models: A Dynamic Thinking Budget Approach
The rise of large reasoning language models (LRLMs) has unlocked new potential for solving complex tasks. These models operate with a thinking budget, that is, a predefined number of reasoning tokens used to arrive at a solution. We propose a novel approach, inspired by the generator/discriminator framework in generative adversarial networks, in which a critic model periodically probes its own reasoning to assess whether it has reached a confident conclusion. If not, reasoning continues until a…

"Google showing a wall of ads before any real results. Facebook promising to “never spy on you,” before evolving into a mass surveillance apparatus. Amazon’s highest-ranked products buoyed by fake reviews."
https://www.theglobeandmail.com/culture/bo

Cory Doctorow coined the term ‘enshittification.’ And he knows how to stop it
The Canadian technology critic remains hopeful a good internet is possible

Learning to Crawl: Latent Model-Based Reinforcement Learning for Soft Robotic Adaptive Locomotion
Vaughn Gzenda, Robin Chhabra
https://arxiv.org/abs/2510.05957 https://

Learning to Crawl: Latent Model-Based Reinforcement Learning for Soft Robotic Adaptive Locomotion
Soft robotic crawlers are mobile robots that utilize soft body deformability and compliance to achieve locomotion through surface contact. Designing control strategies for such systems is challenging due to model inaccuracies, sensor noise, and the need to discover locomotor gaits. In this work, we present a model-based reinforcement learning (MB-RL) framework in which latent dynamics inferred from onboard sensors serve as a predictive model that guides an actor-critic algorithm to optimize loc…

Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR
Jiaming Li, Longze Chen, Ze Gong, Yukun Chen, Lu Wang, Wanwei He, Run Luo, Min Yang
https://arxiv.org/abs/2509.02522

Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR
Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have empowered large language models (LLMs) to tackle challenging reasoning tasks such as mathematics and programming. RLVR leverages verifiable outcome rewards to guide policy optimization, enabling LLMs to progressively improve output quality in a grounded and reliable manner. Despite its promise, the RLVR paradigm poses significant challenges, as existing methods often suffer from sparse reward signals and unstable poli…

Amidst the mayhem of the Johnson/Truss/Sunak years I once posted on X that I could not tweet as fast as new scandals occurred.
I feel the same about Trump’s America today
– where every day brings some new outrage, that would normally be enough to bring any other President down.
Republican members of Congress would be baying for blood if a Democrat President committed even a fraction of the outrages which Donald Trump seems to get away with, time and again.

The Madness of King Donald
After the recent bewildering slew of Trump administration outrages, Alexandra Hall Hall questions conservative commentator and fierce Trump critic Bill Kristol

Kristi Noem Says ICE Will Be ‘All Over’ the Super Bowl https://www.nytimes.com/2025/10/04/arts/music/ice-bad-bunny-super-bowl.html

Known Cowboys critic sees the light, praises Dak Prescott for MVP-caliber season https://www.si.com/nfl/cowboys/news/known-cowboys-critic-sees-the-light-praises-dak-prescott-for-mvp-caliber-season

From Learning to Mastery: Achieving Safe and Efficient Real-World Autonomous Driving with Human-In-The-Loop Reinforcement Learning
Li Zeqiao, Wang Yijing, Wang Haoyu, Li Zheng, Li Peng, Liu Wenfei, Zuo Zhiqiang
https://arxiv.org/abs/2510.06038

From Learning to Mastery: Achieving Safe and Efficient Real-World Autonomous Driving with Human-In-The-Loop Reinforcement Learning
Autonomous driving with reinforcement learning (RL) has significant potential. However, applying RL in real-world settings remains challenging due to the need for safe, efficient, and robust learning. Incorporating human expertise into the learning process can help overcome these challenges by reducing risky exploration and improving sample efficiency. In this work, we propose a reward-free, active human-in-the-loop learning method called Human-Guided Distributional Soft Actor-Critic (H-DSAC). …

Jesus. The russian federation disrupted GPS signals for the President of EU’s plane and he’s trying to make jokes about it. 😳🤦‍♂️
https://apnews.com/article/europe-leyen-plane-radar-russia-jammed-51fa78294c2d0464dce5fd24dd4f273b …

Russia is suspected of jamming navigation on EU leader’s plane above Bulgaria, an official says
A plane carrying European Commission President Ursula von der Leyen was hit by GPS jamming over Bulgaria in a suspected Russian operation. A spokesperson confirmed the incident on Monday. The plane landed safely at Plovdiv airport. Von der Leyen will continue her planned tour of the European Union’s nations bordering Russia and Belarus, according to the commission's spokesperson Arianna Podestà. Von der Leyen, a fierce critic of Russian President Vladimir Putin and Moscow’s war in Ukraine,…

I am not a "tech critic". I am an antifascist, a feminist, an anticapitalist, an engineer. My criticism of tech flows from my politics and values. Not from a desire to save or destroy tech. Tech is an expression of power and that's what the whole conversation is about.

The latest Presidential memo, “Countering Domestic Terrorism and Organized Political Violence" is a declaration of war on the so-called “radical left, and accuses any critic of law enforcement, or gov't activities of basically fomenting “violent revolution.”
The Trump administration’s designation today of antifa as a terrorist group allows the state to brand all dissidents as supporters of #antifa

Trump’s War on America
Trump’s newest presidential memoranda criminalizes critics of empire, capitalism, Christian nationalism, abuses by the state and those who fight racism and gender discrimination.

Critical Line Item With Tom Ravlic
Tom Ravlic FIPA has looked at complex issues in business, finance and politics for a range of publications over two decades...
Great Australian Pods Podcast Directory: https://www.greataustralianpods.com/critical-line-item/

Multi-Actor Multi-Critic Deep Deterministic Reinforcement Learning with a Novel Q-Ensemble Method
Andy Wu, Chun-Cheng Lin, Rung-Tzuo Liaw, Yuehua Huang, Chihjung Kuo, Chia Tong Weng
https://arxiv.org/abs/2510.01083

Multi-Actor Multi-Critic Deep Deterministic Reinforcement Learning with a Novel Q-Ensemble Method
Reinforcement learning has gathered much attention in recent years due to its rapid development and rich applications, especially on control systems and robotics. When tackling real-world applications with reinforcement learning method, the corresponded Markov decision process may have huge discrete or even continuous state/action space. Deep reinforcement learning has been studied for handling these issues through deep learning for years, and one promising branch is the actor-critic architectu…

Learning Mean-Field Games through Mean-Field Actor-Critic Flow
Mo Zhou, Haosheng Zhou, Ruimeng Hu
https://arxiv.org/abs/2510.12180 https://arxiv.org/pdf/25…

Learning Mean-Field Games through Mean-Field Actor-Critic Flow
We propose the Mean-Field Actor-Critic (MFAC) flow, a continuous-time learning dynamics for solving mean-field games (MFGs), combining techniques from reinforcement learning and optimal transport. The MFAC framework jointly evolves the control (actor), value function (critic), and distribution components through coupled gradient-based updates governed by partial differential equations (PDEs). A central innovation is the Optimal Transport Geodesic Picard (OTGP) flow, which drives the distributio…

Cultural criticism is at risk of erasure, as the Chicago Tribune cut its film critic job, VF fired its film critic, and the NYT reassigned four arts critics (Jesse Hassenger/The Guardian)
https://www.theguardian.com/culture/2025/aug/26/movie-reviews-c…

A profile of Anthropic CEO Dario Amodei, a critic of Trump and David Sacks' AI agenda, arguing its hands-off approach could steer AI down a dangerous path (Wall Street Journal)
https://www.wsj.com/tech/ai/ai-anthropic-d

Unlocking the Potential of Soft Actor-Critic for Imitation Learning
Nayari Marie Lessa, Melya Boukheddimi, Frank Kirchner
https://arxiv.org/abs/2509.24539 https://

Unlocking the Potential of Soft Actor-Critic for Imitation Learning
Learning-based methods have enabled robots to acquire bio-inspired movements with increasing levels of naturalness and adaptability. Among these, Imitation Learning (IL) has proven effective in transferring complex motion patterns from animals to robotic systems. However, current state-of-the-art frameworks predominantly rely on Proximal Policy Optimization (PPO), an on-policy algorithm that prioritizes stability over sample efficiency and policy generalization. This paper proposes a novel IL f…

Days after attorney general Pam Bondi tried to put an end to the Justice Department’s revelations about Jeffrey Epstein, captains of the legal resistance gathered by Zoom.
Norm Eisen, a former attorney for Barack Obama’s White House, had convened lawyers, Democratic communications strategists, a neoconservative Trump critic, and a former chair of the Michigan Democratic Party.
This one was big, Eisen said from his parked car in Baltimore, where he had traveled for a lawsuit to ov…

The Anti-Trump Resistance That’s Actually Working
A flurry of lawsuits is challenging Trump in the court of law and the court of public opinion.

I've always been a critic of "Stoicism for the military" events and talks. I think the military often abuses a philosophy whose core aspects include cosmopolitanism and that pushes people to do the right thing, especially against power.
But I am ready to be proved wrong by all the guys filling Ryan Holiday's rooms, standing up for "justice" against bombing fishermen in the Caribbean.
Any minute now.

Does anybody remember Film Critic Hulk? What happened to him (or her)?
#movies #FilmCriticHulk #BirthMoviesDeath

New reporting on Monday detailed just how much US Immigration and Customs Enforcement has spent on weaponry since Donald Trump took office
—weapons that have been purchased as the administration has turned federal agents on US cities such as Chicago and Portland, illustrating how the president is treating increasingly armed ICE officers as his
“private military,” as one progressive critic said.
The agency spent $71,515,762 on small arms from January 20—the day Trump began his…

Trump’s ICE jacks up weapons spending by 700%—including ‘guided missile warheads’
“ICE was always going to be Trump’s private military to deploy domestically against Americans,” said one critic.

XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning
Daniel Palenicek, Florian Vogt, Joe Watson, Ingmar Posner, Jan Peters
https://arxiv.org/abs/2509.25174

XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning
Sample efficiency is a central property of effective deep reinforcement learning algorithms. Recent work has improved this through added complexity, such as larger models, exotic network architectures, and more complex algorithms, which are typically motivated purely by empirical performance. We take a more principled approach by focusing on the optimization landscape of the critic network. Using the eigenspectrum and condition number of the critic's Hessian, we systematically investigate the i…

Applying reinforcement learning to optical cavity locking tasks: considerations on actor-critic architectures and real-time hardware implementation
Mateusz Bawaj, Andrea Svizzeretto
https://arxiv.org/abs/2509.14884

Applying reinforcement learning to optical cavity locking tasks: considerations on actor-critic architectures and real-time hardware implementation
This proceedings contains our considerations made during and after fruitful discussions held at EuCAIFCon 2025. We explore the use of deep reinforcement learning for autonomous locking of Fabry-Perot optical cavities in non-linear regimes, with relevance to gravitational-wave detectors. A custom Gymnasium environment with a time-domain simulator enabled training of agents such as deep deterministic policy gradient, achieving reliable lock acquisition for both low- and high-finesse cavities, inc…

A Critic of Universities Is Rallying to Defend Them in the Trump Era - The New York Times
https://archive.ph/3alQc

🔊 #NowPlaying on #BBCRadio3:
#PrivatePassions
- Mark Kermode
Michael Berkeley's guest is the film critic Mark Kermode
Relisten now 👇
https://www.bbc.co.uk/programmes/m002j4p0

Scalable Fairness Shaping with LLM-Guided Multi-Agent Reinforcement Learning for Peer-to-Peer Electricity Markets
Shrenik Jadhav, Birva Sevak, Srijita Das, Akhtar Hussain, Wencong Su, Van-Hai Bui
https://arxiv.org/abs/2508.18610

Scalable Fairness Shaping with LLM-Guided Multi-Agent Reinforcement Learning for Peer-to-Peer Electricity Markets
Peer-to-peer (P2P) energy trading is becoming central to modern distribution systems as rooftop PV and home energy management systems become pervasive, yet most existing market and reinforcement learning designs emphasize efficiency or private profit and offer little real-time guidance to ensure equitable outcomes under uncertainty. To address this gap, a fairness-aware multiagent reinforcement learning framework, FairMarket-RL, is proposed in which a large language model (LLM) critic shapes bi…

Actor-Critic for Continuous Action Chunks: A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse Reward
Jiarui Yang, Bin Zhu, Jingjing Chen, Yu-Gang Jiang
https://arxiv.org/abs/2508.11143

Actor-Critic for Continuous Action Chunks: A Reinforcement Learning Framework for Long-Horizon Robotic Manipulation with Sparse Reward
Existing reinforcement learning (RL) methods struggle with long-horizon robotic manipulation tasks, particularly those involving sparse rewards. While action chunking is a promising paradigm for robotic manipulation, using RL to directly learn continuous action chunks in a stable and data-efficient manner remains a critical challenge. This paper introduces AC3 (Actor-Critic for Continuous Chunks), a novel RL framework that learns to generate high-dimensional, continuous action sequences. To mak…

Quantum Reinforcement Learning-Guided Diffusion Model for Image Synthesis via Hybrid Quantum-Classical Generative Model Architectures
Chi-Sheng Chen, En-Jui Kuo
https://arxiv.org/abs/2509.14163

Quantum Reinforcement Learning-Guided Diffusion Model for Image Synthesis via Hybrid Quantum-Classical Generative Model Architectures
Diffusion models typically employ static or heuristic classifier-free guidance (CFG) schedules, which often fail to adapt across timesteps and noise conditions. In this work, we introduce a quantum reinforcement learning (QRL) controller that dynamically adjusts CFG at each denoising step. The controller adopts a hybrid quantum--classical actor--critic architecture: a shallow variational quantum circuit (VQC) with ring entanglement generates policy features, which are mapped by a compact multil…

A profile of podcaster and writer Ed Zitron: tech journalism is flawed, his brash AI critic persona is not a mask, his PR firm gives him insider insight, more (Tabby Kinder/Financial Times)
https://www.ft.com/content/4c8d6420-d088-4660-8973-c4996cd990fb

Code Driven Planning with Domain-Adaptive Critic
Zikang Tian, Shaohui Peng, Du Huang, Jiaming Guo, Ruizhi Chen, Rui Zhang, Xishan Zhang, Yuxuan Guo, Zidong Du, Qi Guo, Ling Li, Yewen Pu, Xing Hu, Yunji Chen
https://arxiv.org/abs/2509.19077

As a critic of Albion Online I can now feel I can say stuff I didn't say before because I was a stupid fanboy.
ie. when they removed the button to mount your horse on controller, that was a MAJOR BLUNDER and the first step into "unskilled development".
I'm gonna keep some accounts just in case people are gonna play this trash...but for now it seems like Albion Online is going to stay in my trash bin.

Source-Condition Analysis of Kernel Adversarial Estimators
Antonio Olivas-Martinez, Andrea Rotnitzky
https://arxiv.org/abs/2508.17181 https://arxiv.org/pdf…

Source-Condition Analysis of Kernel Adversarial Estimators
In many applications, the target parameter depends on a nuisance function defined by a conditional moment restriction, whose estimation often leads to an ill-posed inverse problem. Classical approaches, such as sieve-based GMM, approximate the restriction using a fixed set of test functions and may fail to capture important aspects of the solution. Adversarial estimators address this limitation by framing estimation as a game between an estimator and an adaptive critic. We study the class of Re…

Oh wow, there's a new Mr. Plinkett video!
(For those who don't know, that "movie critic" persona was created for an epic takedown of StarWars episodes 1-3 in the early era of youtube. For me and probably many others it was the first time they saw funny but smart long-form video essays about culture and media.)
https://www.

Hybrid Learning and Optimization methods for solving Capacitated Vehicle Routing Problem
Monit Sharma, Hoong Chuin Lau
https://arxiv.org/abs/2509.15262 https://

Hybrid Learning and Optimization methods for solving Capacitated Vehicle Routing Problem
The Capacitated Vehicle Routing Problem (CVRP) is a fundamental NP-hard problem in logistics. Augmented Lagrangian Methods (ALM) for solving CVRP performance depends heavily on well-tuned penalty parameters. In this paper, we propose a hybrid optimization approach that integrates deep reinforcement learning (RL) to automate the selection of penalty parameter values within both classical (RL-C-ALM) and quantum-enhanced (RL-Q-ALM) ALM solvers. Using Soft Actor-Critic, our approach learns penalty …

ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding
Yuhang Li, Chenchen Zhang, Ruilin Lv, Ao Liu, Ken Deng, Yuanxing Zhang, Jiaheng Liu, Wiggin Zhou, Bo Zhou
https://arxiv.org/abs/2510.11498

ReLook: Vision-Grounded RL with a Multimodal LLM Critic for Agentic Web Coding
While Large Language Models (LLMs) excel at algorithmic code generation, they struggle with front-end development, where correctness is judged on rendered pixels and interaction. We present ReLook, an agentic, vision-grounded reinforcement learning framework that empowers an agent to close a robust generate--diagnose--refine loop by invoking a multimodal LLM (MLLM) as a tool. During training, the agent uses the MLLM-in-the-loop both as a visual critic--scoring code with screenshots--and as a so…

Fully Spiking Actor-Critic Neural Network for Robotic Manipulation
Liwen Zhang, Heng Deng, Guanghui Sun
https://arxiv.org/abs/2508.12038 https://arxiv.org/…

Fully Spiking Actor-Critic Neural Network for Robotic Manipulation
This study proposes a hybrid curriculum reinforcement learning (CRL) framework based on a fully spiking neural network (SNN) for 9-degree-of-freedom robotic arms performing target reaching and grasping tasks. To reduce network complexity and inference latency, the SNN architecture is simplified to include only an input and an output layer, which shows strong potential for resource-constrained environments. Building on the advantages of SNNs-high inference speed, low energy consumption, and spik…

I've always been a critic of "Stoicism for the military" events and talks. I think the military often abuses a philosophy whose core aspects include cosmopolitanism and that pushes people to do the right thing, especially against power.
But I am ready to be proved wrong by all the guys filling Ryan Holiday's rooms, standing up for "justice" against bombing fishermen in the Caribbean.
Any minute now.

Sampling Complexity of TD and PPO in RKHS
Lu Zou, Wendi Ren, Weizhong Zhang, Liang Ding, Shuang Li
https://arxiv.org/abs/2509.24991 https://arxiv.org/pdf/2…

Sampling Complexity of TD and PPO in RKHS
We revisit Proximal Policy Optimization (PPO) from a function-space perspective. Our analysis decouples policy evaluation and improvement in a reproducing kernel Hilbert space (RKHS): (i) A kernelized temporal-difference (TD) critic performs efficient RKHS-gradient updates using only one-step state-action transition samples; (ii) a KL-regularized, natural-gradient policy step exponentiates the evaluated action-value, recovering a PPO/TRPO-style proximal update in continuous state-action spaces.…

Trump’s former adviser turned critic John Bolton expected to be criminally charged as early as next week: report | The Independent
https://www.independent.co.uk/news/world/americas/us-politics/trump-national-security-adviser-john-bolton-indicted-b2843581.html

Report: Rolling Stone has laid off some staff, including executive digital director Lisa Tozzi, chief TV critic Alan Sepinwall, and copy chief Steve Pearl (Ross A. Lincoln/The Wrap)
https://www.thewrap.com/rolling-stone-hit-with-layoffs-amid-on…

Rolling Stone Hit With Layoffs Amid Ongoing Staff Reductions at Penske
Executive digital director Lisa Tozzi, chief television critic Alan Sepinwall and copy chief Steven Pearl are among those let go

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models
Runpeng Dai, Linfeng Song, Haolin Liu, Zhenwen Liang, Dian Yu, Haitao Mi, Zhaopeng Tu, Rui Liu, Tong Zheng, Hongtu Zhu, Dong Yu
https://arxiv.org/abs/2509.09675

CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models
Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful paradigm for enhancing the reasoning ability of Large Language Models (LLMs). Yet current RLVR methods often explore poorly, leading to premature convergence and entropy collapse. To address this challenge, we introduce Curiosity-Driven Exploration (CDE), a framework that leverages the model's own intrinsic sense of curiosity to guide exploration. We formalize curiosity with signals from both the actor and the critic: for the a…

Pretraining in Actor-Critic Reinforcement Learning for Robot Motion Control
Jiale Fan, Andrei Cramariuc, Tifanny Portela, Marco Hutter
https://arxiv.org/abs/2510.12363 https://

Pretraining in Actor-Critic Reinforcement Learning for Robot Motion Control
The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years. However, in the domain of reinforcement learning (RL) for robot motion control, individual skills are often learned from scratch despite the high likelihood that some generalizable knowledge is shared across all task-specific policies belonging to a single robot embodiment. This work aims to define a paradigm for pretraining neural network models that enc…

Replaced article(s) found for eess.SY. https://arxiv.org/list/eess.SY/new
[1/1]:
- Self-Tuning PID Control via a Hybrid Actor-Critic-Based Neural Structure for Quadcopter Control
Iman Sharifi, Aria Alasty

OPTIC-ER: A Reinforcement Learning Framework for Real-Time Emergency Response and Equitable Resource Allocation in Underserved African Communities
Mary Tonwe
https://arxiv.org/abs/2508.12943

OPTIC-ER: A Reinforcement Learning Framework for Real-Time Emergency Response and Equitable Resource Allocation in Underserved African Communities
Public service systems in many African regions suffer from delayed emergency response and spatial inequity, causing avoidable suffering. This paper introduces OPTIC-ER, a reinforcement learning (RL) framework for real-time, adaptive, and equitable emergency response. OPTIC-ER uses an attention-guided actor-critic architecture to manage the complexity of dispatch environments. Its key innovations are a Context-Rich State Vector, encoding action sub-optimality, and a Precision Reward Function, wh…

🇺🇦 #NowPlaying on #BBC6Music's #DonLettsCultureClashRadio
Black Samurai:
🎵 Information Critic Jungle (Benny Page Remix) (feat. Daddy Freddy & Ragga Twins)
#BlackSamurai

“In the 21st century, the Antichrist is a Luddite who wants to stop all science. It’s someone like Greta or Eliezer,” he said, referring to Thunberg and Eliezer Yudkowsky, a prominent critic of the tech industry’s approach to AI"
What billionaire Peter Thiel said in his private ‘Antichrist lectures’ - The Washington Post
https://archive.ph/dHfRl

MusicSwarm: Biologically Inspired Intelligence for Music Composition
Markus J. Buehler
https://arxiv.org/abs/2509.11973 https://arxiv.org/pdf/2509.11973

MusicSwarm: Biologically Inspired Intelligence for Music Composition
We show that coherent, long-form musical composition can emerge from a decentralized swarm of identical, frozen foundation models that coordinate via stigmergic, peer-to-peer signals, without any weight updates. We compare a centralized multi-agent system with a global critic to a fully decentralized swarm in which bar-wise agents sense and deposit harmonic, rhythmic, and structural cues, adapt short-term memory, and reach consensus. Across symbolic, audio, and graph-theoretic analyses, the swa…

From Tabula Rasa to Emergent Abilities: Discovering Robot Skills via Real-World Unsupervised Quality-Diversity
Luca Grillotti (AIRL, Imperial College London), Lisa Coiffard (AIRL, Imperial College London), Oscar Pang (AIRL, Imperial College London), Maxence Faldor (AIRL, Imperial College London), Antoine Cully (AIRL, Imperial College London)
https://

From Tabula Rasa to Emergent Abilities: Discovering Robot Skills via Real-World Unsupervised Quality-Diversity
Autonomous skill discovery aims to enable robots to acquire diverse behaviors without explicit supervision. Learning such behaviors directly on physical hardware remains challenging due to safety and data efficiency constraints. Existing methods, including Quality-Diversity Actor-Critic (QDAC), require manually defined skill spaces and carefully tuned heuristics, limiting real-world applicability. We propose Unsupervised Real-world Skill Acquisition (URSA), an extension of QDAC that enables rob…

MPC-based Deep Reinforcement Learning Method for Space Robotic Control with Fuel Sloshing Mitigation
Mahya Ramezani, M. Amin Alandihallaj, Bar{\i}\c{s} Can Yal\c{c}{\i}n, Miguel Angel Olivares Mendez, Holger Voos
https://arxiv.org/abs/2509.21045

MPC-based Deep Reinforcement Learning Method for Space Robotic Control with Fuel Sloshing Mitigation
This paper presents an integrated Reinforcement Learning (RL) and Model Predictive Control (MPC) framework for autonomous satellite docking with a partially filled fuel tank. Traditional docking control faces challenges due to fuel sloshing in microgravity, which induces unpredictable forces affecting stability. To address this, we integrate Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) RL algorithms with MPC, leveraging MPC's predictive capabilities to accelerate RL training a…

Off Policy Lyapunov Stability in Reinforcement Learning
Sarvan Gill, Daniela Constantinescu
https://arxiv.org/abs/2509.09863 https://arxiv.org/pdf/2509.098…

Off Policy Lyapunov Stability in Reinforcement Learning
Traditional reinforcement learning lacks the ability to provide stability guarantees. More recent algorithms learn Lyapunov functions alongside the control policies to ensure stable learning. However, the current self-learned Lyapunov functions are sample inefficient due to their on-policy nature. This paper introduces a method for learning Lyapunov functions off-policy and incorporates the proposed off-policy Lyapunov function into the Soft Actor Critic and Proximal Policy Optimization algorit…

Biased-Attention Guided Risk Prediction for Safe Decision-Making at Unsignalized Intersections
Chengyang Dong, Nan Guo
https://arxiv.org/abs/2510.12428 https://

Biased-Attention Guided Risk Prediction for Safe Decision-Making at Unsignalized Intersections
Autonomous driving decision-making at unsignalized intersections is highly challenging due to complex dynamic interactions and high conflict risks. To achieve proactive safety control, this paper proposes a deep reinforcement learning (DRL) decision-making framework integrated with a biased attention mechanism. The framework is built upon the Soft Actor-Critic (SAC) algorithm. Its core innovation lies in the use of biased attention to construct a traffic risk predictor. This predictor assesses …

$K$-Level Policy Gradients for Multi-Agent Reinforcement Learning
Aryaman Reddi, Gabriele Tiboni, Jan Peters, Carlo D'Eramo
https://arxiv.org/abs/2509.12117 https://

$K$-Level Policy Gradients for Multi-Agent Reinforcement Learning
Actor-critic algorithms for deep multi-agent reinforcement learning (MARL) typically employ a policy update that responds to the current strategies of other agents. While being straightforward, this approach does not account for the updates of other agents at the same update step, resulting in miscoordination. In this paper, we introduce the $K$-Level Policy Gradient (KPG), a method that recursively updates each agent against the updated policies of other agents, speeding up the discovery of ef…

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/4]:
- SegDAC: Segmentation-Driven Actor-Critic for Visual Reinforcement Learning
Alexandre Brown, Glen Berseth

TLE-Based A2C Agent for Terrestrial Coverage Orbital Path Planning
Anantha Narayanan, Battu Bhanu Teja, Pruthwik Mishra
https://arxiv.org/abs/2508.10872 https://

TLE-Based A2C Agent for Terrestrial Coverage Orbital Path Planning
The increasing congestion of Low Earth Orbit (LEO) poses persistent challenges to the efficient deployment and safe operation of Earth observation satellites. Mission planners must now account not only for mission-specific requirements but also for the increasing collision risk with active satellites and space debris. This work presents a reinforcement learning framework using the Advantage Actor-Critic (A2C) algorithm to optimize satellite orbital parameters for precise terrestrial coverage wi…

Quantum Machine Learning, Quantitative Trading, Reinforcement Learning, Deep Learning
Jun-Hao Chen, Yu-Chien Huang, Yun-Cheng Tsai, Samuel Yen-Chi Chen
https://arxiv.org/abs/2509.09176

Quantum Machine Learning, Quantitative Trading, Reinforcement Learning, Deep Learning
The convergence of quantum-inspired neural networks and deep reinforcement learning offers a promising avenue for financial trading. We implemented a trading agent for USD/TWD by integrating Quantum Long Short-Term Memory (QLSTM) for short-term trend prediction with Quantum Asynchronous Advantage Actor-Critic (QA3C), a quantum-enhanced variant of the classical A3C. Trained on data from 2000-01-01 to 2025-04-30 (80\% training, 20\% testing), the long-only agent achieves 11.87\% return over aroun…

CRADLE: Conversational RTL Design Space Exploration with LLM-based Multi-Agent Systems
Lukas Krupp, Maximilian Sch\"offel, Elias Biehl, Norbert Wehn
https://arxiv.org/abs/2508.08709

CRADLE: Conversational RTL Design Space Exploration with LLM-based Multi-Agent Systems
This paper presents CRADLE, a conversational framework for design space exploration of RTL designs using LLM-based multi-agent systems. Unlike existing rigid approaches, CRADLE enables user-guided flows with internal self-verification, correction, and optimization. We demonstrate the framework with a generator-critic agent system targeting FPGA resource minimization using state-of-the-art LLMs. Experimental results on the RTLLM benchmark show that CRADLE achieves significant reductions in resou…