Tootfinder

Hierarchical Reinforcement Learning Framework for Adaptive Walking Control Using General Value Functions of Lower-Limb Sensor Signals
Sonny T. Jones, Grange M. Simpson, Patrick M. Pilarski, Ashley N. Dalrymple
https://arxiv.org/abs/2507.16983

Hierarchical Reinforcement Learning Framework for Adaptive Walking Control Using General Value Functions of Lower-Limb Sensor Signals
Rehabilitation technology is a natural setting to study the shared learning and decision-making of human and machine agents. In this work, we explore the use of Hierarchical Reinforcement Learning (HRL) to develop adaptive control strategies for lower-limb exoskeletons, aiming to enhance mobility and autonomy for individuals with motor impairments. Inspired by prominent models of biological sensorimotor processing, our investigated HRL approach breaks down the complex task of exoskeleton contro…

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
Zengzhi Wang, Fan Zhou, Xuefeng Li, Pengfei Liu
https://arxiv.org/abs/2506.20512 http…

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
Different base language model families, such as Llama and Qwen, exhibit divergent behaviors during post-training with reinforcement learning (RL), especially on reasoning-intensive tasks. What makes a base language model suitable for reinforcement learning? Gaining deeper insight into this question is essential for developing RL-scalable foundation models of the next generation. In this work, we investigate how mid-training strategies shape RL dynamics, focusing on two representative model fami…

A Principled Path to Fitted Distributional Evaluation
Sungee Hong, Jiayi Wang, Zhengling Qi, Raymond Ka Wai Wong
https://arxiv.org/abs/2506.20048 https://

A Principled Path to Fitted Distributional Evaluation
In reinforcement learning, distributional off-policy evaluation (OPE) focuses on estimating the return distribution of a target policy using offline data collected under a different policy. This work focuses on extending the widely used fitted-Q evaluation -- developed for expectation-based reinforcement learning -- to the distributional OPE setting. We refer to this extension as fitted distributional evaluation (FDE). While only a few related approaches exist, there remains no unified framewor…

Study of $p_\mathrm{T}$-differential radial flow in blast-wave model
Swati Saha, Ranbir Singh, Bedangadas Mohanty
https://arxiv.org/abs/2505.19697 https://…

Study of $p_\mathrm{T}$-differential radial flow in blast-wave model
The transverse momentum-differential radial flow observable $v_0(p_\mathrm{T})$, recently proposed and measured by the ATLAS and ALICE collaborations, provides a novel tool to probe radial expansion dynamics in high-energy heavy-ion collisions. In this work, we conduct a detailed study of $v_0(p_\mathrm{T})$ using a blast-wave model that incorporates hydrodynamic-like expansion and thermal emission. We introduce event-by-event fluctuations in the transverse expansion velocity and kinetic freeze…

On the One-Loop Exactness of Gravity Partition Function
Andres Goya, Mauricio Leston, Mario Passaglia
https://arxiv.org/abs/2507.16141 https://

On the One-Loop Exactness of Gravity Partition Function
In a previous work, we showed that the two- and three-loop contributions to the partition function of three-dimensional gravity in flat space vanish. This is in agreement with the expected one-loop exactness dictated by the underlying symmetry at the quantum level. To highlight the distinctive nature of the $D=3$ case, we extend the three-loop computation to arbitrary spacetime dimensions $D$. In higher dimensions, the number of contributions increases substantially, reinforcing the view that o…

Another of my forays into AI ethics is just out! This time the focus is on the ethics (or lack thereof) of Reinforcement Learning Feedback (RLF) techniques aimed at increasing the 'alignment' of LLMs.
The paper is fruit of the joint work of a great team of collaborators, among whom @… and @…

Helpful, harmless, honest? Sociotechnical limits of AI alignment and safety through Reinforcement Learning from Human Feedback - Ethics and Information Technology
This paper critically evaluates the attempts to align Artificial Intelligence (AI) systems, especially Large Language Models (LLMs), with human values and intentions through Reinforcement Learning from Feedback methods, involving either human feedback (RLHF) or AI feedback (RLAIF). Specifically, we show the shortcomings of the broadly pursued alignment goals of honesty, harmlessness, and helpfulness. Through a multidisciplinary sociotechnical critique, we examine both the theoretical underpinni…

Robots and Children that Learn Together : Improving Knowledge Retention by Teaching Peer-Like Interactive Robots
Imene Tarakli, Samuele Vinanzi, Richard Moore, Alessandro Di Nuovo
https://arxiv.org/abs/2506.18365

Robots and Children that Learn Together : Improving Knowledge Retention by Teaching Peer-Like Interactive Robots
Despite growing interest in Learning-by-Teaching (LbT), few studies have explored how this paradigm can be implemented with autonomous, peer-like social robots in real classrooms. Most prior work has relied on scripted or Wizard-of-Oz behaviors, limiting our understanding of how real-time, interactive learning can be supported by artificial agents. This study addresses this gap by introducing Interactive Reinforcement Learning (RL) as a cognitive model for teachable social robots. We conducted …

Towards Microgrid Resilience Enhancement via Mobile Power Sources and Repair Crews: A Multi-Agent Reinforcement Learning Approach
Yi Wang, Dawei Qiu, Fei Teng, Goran Strbac
https://arxiv.org/abs/2507.18095

Towards Microgrid Resilience Enhancement via Mobile Power Sources and Repair Crews: A Multi-Agent Reinforcement Learning Approach
Mobile power sources (MPSs) have been gradually deployed in microgrids as critical resources to coordinate with repair crews (RCs) towards resilience enhancement owing to their flexibility and mobility in handling the complex coupled power-transport systems. However, previous work solves the coordinated dispatch problem of MPSs and RCs in a centralized manner with the assumption that the communication network is still fully functioning after the event. However, there is growing evidence that ce…

Checklists Are Better Than Reward Models For Aligning Language Models
Vijay Viswanathan, Yanchao Sun, Shuang Ma, Xiang Kong, Meng Cao, Graham Neubig, Tongshuang Wu
https://arxiv.org/abs/2507.18624

Checklists Are Better Than Reward Models For Aligning Language Models
Language models must be adapted to understand and follow user instructions. Reinforcement learning is widely used to facilitate this -- typically using fixed criteria such as "helpfulness" and "harmfulness". In our work, we instead propose using flexible, instruction-specific criteria as a means of broadening the impact that reinforcement learning can have in eliciting instruction following. We propose "Reinforcement Learning from Checklist Feedback" (RLCF). From instructions, we extract checkl…

AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control
Ruosen Li, Ziming Luo, Quan Zhang, Ruochen Li, Ben Zhou, Ali Payani, Xinya Du
https://arxiv.org/abs/2506.20160

AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control
Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts, but this "overthinking" incurs high latency and cost without commensurate accuracy gains. In this work, we introduce AALC, a lightweight, accuracy-aware length reward integrated into reinforcement learning that dynamically balances correctness and brevity during training. By incorporating validation accuracy into the reward and employing a smooth, dynamically scheduled length penalty…