paper-with-me

Papers

Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data

2025-07-11 · Jeonghye Kim, Yongjae Shin, Whiyoung Jung, Sunghoon Hong, Deunsol Yoon, Youngchul Sung, Kanghoon Lee, Woohyung Lim arxiv

Reinforcement learning with offline data suffers from Q-value extrapolation errors. To address this issue, we first demonstrate that linear extrapolation of the Q-function beyond the data range is particularly problematic. To mitigate this, we propose guiding the gradual decrease of Q-values outside the data range, which is achieved through reward scaling with layer normalization (RS-LN) and a penalization mechanism for infeasible actions (PA). By combining RS-LN and PA, we develop a new algorithm called PARS. We evaluate PARS across a range of tasks, demonstrating superior performance compared to state-of-the-art algorithms in both offline training and online fine-tuning on the D4RL benchmark, with notable success in the challenging AntMaze Ultra task.

📄 PDF Abstract BibTeX arXiv:2507.08761

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewards

2026-03-18 · Ruixiang Wang, Qingming Liu, Yueci Deng, Guiliang Liu 외 arxiv

Video generative models are increasingly used as world models for robotics, where a model generates a future visual rollout conditioned on the current observation and task instruction, and an inverse dynamics model (IDM)…

Video GenerationVideo Alignment

Which Rewards Matter? Reward Selection for Reinforcement Learning under Limited Feedback

2025-09-30 · Shreyas Chaudhari, Renhao Zhang, Philip S. Thomas, Bruno Castro da Silva arxiv

The ability of reinforcement learning algorithms to learn effective policies is determined by the rewards available during training. However, for practical problems, obtaining large quantities of reward labels is often i…

Reinforcement Learning

Anti-Exploration by Random Network Distillation

2023-01-31 · Alexander Nikulin, Vladislav Kurenkov, Denis Tarasov, Sergey Kolesnikov

Despite the success of Random Network Distillation (RND) in various domains, it was shown as not discriminative enough to be used as an uncertainty estimator for penalizing out-of-distribution actions in offline reinforc…

D4RL

Spectral Normalization for Lipschitz-Constrained Policies on Learning Humanoid Locomotion

2025-04-11 · Jaeyong Shin, Woohyun Cha, Donghyeon Kim, Junhyeok Cha 외

Reinforcement learning (RL) has shown great potential in training agile and adaptable controllers for legged robots, enabling them to learn complex locomotion behaviors directly from experience. However, policies trained…

GPUReinforcement Learning (RL)

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents

2026-06-24 · Changdae Oh, Wendi Li, Seongheon Park, Samuel Yeh 외 arxiv

Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-horizon interactions, irreversible actions, and stochastic environmen…

Reinforcement Learning