paper-with-me

홈 › Papers

A Theoretical Justification for Asymmetric Actor-Critic Algorithms

2025-01-31 · Gaspard Lambrechts, Damien Ernst, Aditya Mahajan

In reinforcement learning for partially observable environments, many successful algorithms were developed within the asymmetric learning paradigm. This paradigm leverages additional state information available at training time for faster learning. Although the proposed learning objectives are usually theoretically sound, these methods still lack a theoretical justification for their potential benefits. We propose such a justification for asymmetric actor-critic algorithms with linear function approximators by adapting a finite-time convergence analysis to this setting. The resulting finite-time bound reveals that the asymmetric critic eliminates an error term arising from aliasing in the agent state.

📄 PDF Abstract BibTeX arXiv:2501.19116

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Unbiased Asymmetric Reinforcement Learning under Partial Observability

2021-05-25 · Andrea Baisero, Christopher Amato

In partially observable reinforcement learning, offline training gives access to latent information which is not available during online training and/or execution, such as the system state. Asymmetric actor-critic method…

Partially Observable Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Beyond Procrustes: Balancing-Free Gradient Descent for Asymmetric Low-Rank Matrix Sensing

2021-01-13 · Cong Ma, Yuanxin Li, Yuejie Chi

Low-rank matrix estimation plays a central role in various applications across science and engineering. Recently, nonconvex formulations based on matrix factorization are provably solved by simple gradient descent algori…

Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games

2022-02-18 · ICLR 2022 4 · Dingyang Chen, Yile Li, Qi Zhang

Recent success in cooperative multi-agent reinforcement learning (MARL) relies on centralized training and policy sharing. Centralized training eliminates the issue of non-stationarity MARL yet induces large communicatio…

Multi-agent Reinforcement Learning

A2C is a special case of PPO

2022-05-18 · Shengyi Huang, Anssi Kanervisto, Antonin Raffin, Weixun Wang 외

Advantage Actor-critic (A2C) and Proximal Policy Optimization (PPO) are popular deep reinforcement learning algorithms used for game AI in recent years. A common understanding is that A2C and PPO are separate algorithms …

Deep Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

Variance Reduction in Actor Critic Methods (ACM)

2019-07-23 · Eric Benhamou

After presenting Actor Critic Methods (ACM), we show ACM are control variate estimators. Using the projection theorem, we prove that the Q and Advantage Actor Critic (A2C) methods are optimal in the sense of the $L^2$ no…

Policy Gradient Methods