paper-with-me

Papers

Constrained Policy Optimization with Explicit Behavior Density for Offline Reinforcement Learning

2023-01-28 · NeurIPS 2023 11 · Jing Zhang, Chi Zhang, Wenjia Wang, Bing-Yi Jing

Due to the inability to interact with the environment, offline reinforcement learning (RL) methods face the challenge of estimating the Out-of-Distribution (OOD) points. Existing methods for addressing this issue either control policy to exclude the OOD action or make the $Q$ function pessimistic. However, these methods can be overly conservative or fail to identify OOD areas accurately. To overcome this problem, we propose a Constrained Policy optimization with Explicit Behavior density (CPED) method that utilizes a flow-GAN model to explicitly estimate the density of behavior policy. By estimating the explicit density, CPED can accurately identify the safe region and enable optimization within the region, resulting in less conservative learning policies. We further provide theoretical results for both the flow-GAN estimator and performance guarantee for CPED by showing that CPED can find the optimal $Q$-function value. Empirically, CPED outperforms existing alternatives on various standard offline reinforcement learning tasks, yielding higher expected returns.

📄 PDF Abstract BibTeX arXiv:2301.12130

Code (1)

evalarzj/cped 공식 구현 pytorch

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Supported Trust Region Optimization for Offline Reinforcement Learning

2023-11-15 · Yixiu Mao, Hongchang Zhang, Chen Chen, Yi Xu 외

Offline reinforcement learning suffers from the out-of-distribution issue and extrapolation error. Most policy constraint methods regularize the density of the trained policy towards the behavior policy, which is too res…

MuJoCoreinforcement-learningReinforcement Learning

Supported Policy Optimization for Offline Reinforcement Learning

2022-02-13 · Jialong Wu, Haixu Wu, Zihan Qiu, Jianmin Wang 외

Policy constraint methods to offline reinforcement learning (RL) typically utilize parameterization or regularization that constrains the policy to perform actions within the support set of the behavior policy. The elabo…

Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment

2025-12-30 · Lijun Zhang, Lin Li, Wei Wei, Yajie Qi 외 arxiv

When fine-tuning pre-trained Language Models (LMs) to exhibit desired behaviors, maintaining control over risk is critical for ensuring both safety and trustworthiness. Most existing safety alignment methods, such as Saf…

Density-Ratio Weighted Behavioral Cloning: Learning Control Policies from Corrupted Datasets

2025-10-01 · Shriram Karpoora Sundara Pandian, Ali Baheri arxiv

Offline reinforcement learning (RL) enables policy optimization from fixed datasets, making it suitable for safety-critical applications where online exploration is infeasible. However, these datasets are often contamina…

Reinforcement LearningContinuous ControlOffline RL

First Order Constrained Optimization in Policy Space

2020-02-16 · NeurIPS 2020 12 · Yiming Zhang, Quan Vuong, Keith W. Ross

In reinforcement learning, an agent attempts to learn high-performing behaviors through interacting with the environment, such behaviors are often quantified in the form of a reward function. However some aspects of beha…

Reinforcement Learning