paper-with-me

Papers

A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective

2024-03-12 · Yunpeng Qing, Shunyu Liu, Jingyuan Cong, KaiXuan Chen, Yihe Zhou, Mingli Song

Offline reinforcement learning endeavors to leverage offline datasets to craft effective agent policy without online interaction, which imposes proper conservative constraints with the support of behavior policies to tackle the out-of-distribution problem. However, existing works often suffer from the constraint conflict issue when offline datasets are collected from multiple behavior policies, i.e., different behavior policies may exhibit inconsistent actions with distinct returns across the state space. To remedy this issue, recent advantage-weighted methods prioritize samples with high advantage values for agent training while inevitably ignoring the diversity of behavior policy. In this paper, we introduce a novel Advantage-Aware Policy Optimization (A2PO) method to explicitly construct advantage-aware policy constraints for offline learning under mixed-quality datasets. Specifically, A2PO employs a conditional variational auto-encoder to disentangle the action distributions of intertwined behavior policies by modeling the advantage values of all training data as conditional variables. Then the agent can follow such disentangled action distribution constraints to optimize the advantage-aware policy towards high advantage values. Extensive experiments conducted on both the single-quality and mixed-quality datasets of the D4RL benchmark demonstrate that A2PO yields results superior to the counterparts. Our code is available at https://github.com/Plankson/A2PO

📄 PDF Abstract BibTeX arXiv:2403.07262

Code (1)

plankson/a2po 공식 구현 pytorch

Tasks

D4RLreinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning

2025-05-19 · Hongjoon Ahn, Heewoong Choi, Jisu Han, Taesup Moon

Offline goal-conditioned reinforcement learning (GCRL) offers a practical learning paradigm where goal-reaching policies are trained from abundant unlabeled (reward-free) datasets without additional environment interacti…

VIPO: Value Function Inconsistency Penalized Offline Reinforcement Learning

2025-04-16 · Xuyang Chen, GuoJian Wang, Keyu Yan, Lin Zhao

Offline reinforcement learning (RL) learns effective policies from pre-collected datasets, offering a practical solution for applications where online interactions are risky or costly. Model-based approaches are particul…

D4RLOffline RLreinforcement-learningReinforcement Learning+1

Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems

2020-05-04 · Sergey Levine, Aviral Kumar, George Tucker, Justin Fu

In this tutorial article, we aim to provide the reader with the conceptual tools needed to get started on research on offline reinforcement learning algorithms: reinforcement learning algorithms that utilize previously c…

Decision MakingDeep Reinforcement Learningreinforcement-learningReinforcement Learning+1

CAWR: Corruption-Averse Advantage-Weighted Regression for Robust Policy Optimization

2025-06-18 · Ranting Hu

Offline reinforcement learning (offline RL) algorithms often require additional constraints or penalty terms to address distribution shift issues, such as adding implicit or explicit policy constraints during policy opti…

D4RLOffline RLregression

Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets

2026-05-24 · Zhongjian Qiao, Jiafei Lyu, Chenjia Bai, Peisong Wang 외 arxiv

Cross-domain offline reinforcement learning (RL) aims to learn a policy in the target domain with a limited target domain dataset and a source domain dataset that exhibits a dynamics shift. Training directly on the origi…

Representation LearningReinforcement LearningOffline RL