Tootfinder

Bills getting defensive reinforcements in hopes to avoid 3-game slide https://www.espn.com/nfl/story/_/id/46700557/buffalo-bills-defensive-reinforcements-michael-hoecht-larry-ogunjob-week-8

Evaluation-Aware Reinforcement Learning
Shripad Vilasrao Deshmukh, Will Schwarzer, Scott Niekum
https://arxiv.org/abs/2509.19464 https://arxiv.org/pdf/2509…

Evaluation-Aware Reinforcement Learning
Policy evaluation is often a prerequisite for deploying safety- and performance-critical systems. Existing evaluation approaches frequently suffer from high variance due to limited data and long-horizon tasks, or high bias due to unequal support or inaccurate environmental models. We posit that these challenges arise, in part, from the standard reinforcement learning (RL) paradigm of policy learning without explicit consideration of evaluation. As an alternative, we propose evaluation-aware rei…

Failure Modes of Maximum Entropy RLHF
\"Omer Veysel \c{C}a\u{g}atan, Bar{\i}\c{s} Akg\"un
https://arxiv.org/abs/2509.20265 https://arxiv.org/pdf/…

Failure Modes of Maximum Entropy RLHF
In this paper, we show that Simple Preference Optimization (SimPO) can be derived as Maximum Entropy Reinforcement Learning with length-normalized temperature, providing a theoretical foundation for this reference-free method. Motivated by SimPO's strong performance in offline preference optimization, we investigate whether Maximum Entropy RL can achieve similar results in online RLHF settings. Our experiments find that Maximum Entropy RL consistently exhibits overoptimization and unstable KL d…

Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generation
Chaojun Nie, Jun Zhou, Guanxiang Wang, Shisong Wud, Zichen Wang
https://arxiv.org/abs/2509.20162

Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generation
Large language models (LLMs) often exhibit limited performance on domain-specific tasks due to the natural disproportionate representation of specialized information in their training data and the static nature of these datasets. Knowledge scarcity and temporal lag create knowledge gaps for domain applications. While post-training on domain datasets can embed knowledge into models, existing approaches have some limitations. Continual Pre-Training (CPT) treats all tokens in domain documents with…

From Pheromones to Policies: Reinforcement Learning for Engineered Biological Swarms
Aymeric Vellinger, Nemanja Antonic, Elio Tuci
https://arxiv.org/abs/2509.20095 https://

From Pheromones to Policies: Reinforcement Learning for Engineered Biological Swarms
Swarm intelligence emerges from decentralised interactions among simple agents, enabling collective problem-solving. This study establishes a theoretical equivalence between pheromone-mediated aggregation in \celeg\ and reinforcement learning (RL), demonstrating how stigmergic signals function as distributed reward mechanisms. We model engineered nematode swarms performing foraging tasks, showing that pheromone dynamics mathematically mirror cross-learning updates, a fundamental RL algorithm. E…

MARG: MAstering Risky Gap Terrains for Legged Robots with Elevation Mapping
Yinzhao Dong, Ji Ma, Liu Zhao, Wanyue Li, Peng Lu
https://arxiv.org/abs/2509.20036 https://

MARG: MAstering Risky Gap Terrains for Legged Robots with Elevation Mapping
Deep Reinforcement Learning (DRL) controllers for quadrupedal locomotion have demonstrated impressive performance on challenging terrains, allowing robots to execute complex skills such as climbing, running, and jumping. However, existing blind locomotion controllers often struggle to ensure safety and efficient traversal through risky gap terrains, which are typically highly complex, requiring robots to perceive terrain information and select appropriate footholds during locomotion accurately.…

Learning Robust Penetration-Testing Policies under Partial Observability: A systematic evaluation
Raphael Simon, Pieter Libin, Wim Mees
https://arxiv.org/abs/2509.20008 https://…

Learning Robust Penetration-Testing Policies under Partial Observability: A systematic evaluation
Penetration testing, the simulation of cyberattacks to identify security vulnerabilities, presents a sequential decision-making problem well-suited for reinforcement learning (RL) automation. Like many applications of RL to real-world problems, partial observability presents a major challenge, as it invalidates the Markov property present in Markov Decision Processes (MDPs). Partially Observable MDPs require history aggregation or belief state estimation to learn successful policies. We investi…

A Task-Efficient Reinforcement Learning Task-Motion Planner for Safe Human-Robot Cooperation
Gaoyuan Liu, Joris de Winter, Kelly Merckaert, Denis Steckelmacher, Ann Nowe, Bram Vanderborght
https://arxiv.org/abs/2510.12477

A Task-Efficient Reinforcement Learning Task-Motion Planner for Safe Human-Robot Cooperation
In a Human-Robot Cooperation (HRC) environment, safety and efficiency are the two core properties to evaluate robot performance. However, safety mechanisms usually hinder task efficiency since human intervention will cause backup motions and goal failures of the robot. Frequent motion replanning will increase the computational load and the chance of failure. In this paper, we present a hybrid Reinforcement Learning (RL) planning framework which is comprised of an interactive motion planner and …

Reinforcing Diffusion Models by Direct Group Preference Optimization
Yihong Luo, Tianyang Hu, Jing Tang
https://arxiv.org/abs/2510.08425 https://arxiv.org/…

Reinforcing Diffusion Models by Direct Group Preference Optimization
While reinforcement learning methods such as Group Relative Preference Optimization (GRPO) have significantly enhanced Large Language Models, adapting them to diffusion models remains challenging. In particular, GRPO demands a stochastic policy, yet the most cost-effective diffusion samplers are based on deterministic ODEs. Recent work addresses this issue by using inefficient SDE-based samplers to induce stochasticity, but this reliance on model-agnostic Gaussian noise leads to slow convergenc…

Offline Reinforcement Learning with Generative Trajectory Policies
Xinsong Feng, Leshu Tang, Chenan Wang, Haipeng Chen
https://arxiv.org/abs/2510.11499 https://

Offline Reinforcement Learning with Generative Trajectory Policies
Generative models have emerged as a powerful class of policies for offline reinforcement learning (RL) due to their ability to capture complex, multi-modal behaviors. However, existing methods face a stark trade-off: slow, iterative models like diffusion policies are computationally expensive, while fast, single-step models like consistency policies often suffer from degraded performance. In this paper, we demonstrate that it is possible to bridge this gap. The key to moving beyond the limitati…