paper-with-me

Papers

Average-Reward Reinforcement Learning with Trust Region Methods

2021-06-07 · Xiaoteng Ma, Xiaohang Tang, Li Xia, Jun Yang, Qianchuan Zhao

Most of reinforcement learning algorithms optimize the discounted criterion which is beneficial to accelerate the convergence and reduce the variance of estimates. Although the discounted criterion is appropriate for certain tasks such as financial related problems, many engineering problems treat future rewards equally and prefer a long-run average criterion. In this paper, we study the reinforcement learning problem with the long-run average criterion. Firstly, we develop a unified trust region theory with discounted and average criteria and derive a novel performance bound within the trust region with the Perturbation Analysis (PA) theory. Secondly, we propose a practical algorithm named Average Policy Optimization (APO), which improves the value estimation with a novel technique named Average Value Constraint. Finally, experiments are conducted in the continuous control environment MuJoCo. In most tasks, APO performs better than the discounted PPO, which demonstrates the effectiveness of our approach. Our work provides a unified framework of the trust region approach including both the discounted and average criteria, which may complement the framework of reinforcement learning beyond the discounted objectives.

📄 PDF Abstract BibTeX arXiv:2106.03442

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-controlContinuous ControlMuJoCoreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…

Similar Papers 제목 키워드 기반

Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation

2017-08-17 · NeurIPS 2017 12 · Yuhuai Wu, Elman Mansimov, Shun Liao, Roger Grosse 외

In this work, we propose to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature. We extend the framework of natural policy gradient a…

Atari Gamescontinuous-controlContinuous ControlDeep Reinforcement Learning+4

Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates

2026-05-10 · Anish Diwan, Davide Tateo, Christopher E. Mower, Haitham Bou-Ammar 외 arxiv

Inverse reinforcement learning (IRL) is typically formulated as maximizing entropy subject to matching the distribution of expert trajectories. Classical (dual-ascent) IRL guarantees monotonic performance improvement but…

Reinforcement Learning

Trust-PCL: An Off-Policy Trust Region Method for Continuous Control

2017-07-06 · ICLR 2018 1 · Ofir Nachum, Mohammad Norouzi, Kelvin Xu, Dale Schuurmans

Trust region methods, such as TRPO, are often used to stabilize policy optimization algorithms in reinforcement learning (RL). While current trust region strategies are effective for continuous control, they typically re…

continuous-controlContinuous ControlReinforcement LearningReinforcement Learning (RL)

Trust Region Reward Optimization and Proximal Inverse Reward Optimization Algorithm

2025-09-27 · Yang Chen, Menglin Zou, Jiaqi Zhang, Yitan Zhang 외 arxiv

Inverse Reinforcement Learning (IRL) learns a reward function to explain expert demonstrations. Modern IRL methods often use the adversarial (minimax) formulation that alternates between reward and policy optimization, w…

Reinforcement Learning

Embedding Safety into RL: A New Take on Trust Region Methods

2024-11-05 · Nikola Milosevic, Johannes Müller, Nico Scherf

Reinforcement Learning (RL) agents can solve diverse tasks but often exhibit unsafe behavior. Constrained Markov Decision Processes (CMDPs) address this by enforcing safety constraints, yet existing methods either sacrif…

Reinforcement Learning (RL)