paper-with-me

Papers

ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization

2024-02-22 · Tianying Ji, Yongyuan Liang, Yan Zeng, Yu Luo, Guowei Xu, Jiawei Guo, Ruijie Zheng, Furong Huang, Fuchun Sun, Huazhe Xu

The varying significance of distinct primitive behaviors during the policy learning process has been overlooked by prior model-free RL algorithms. Leveraging this insight, we explore the causal relationship between different action dimensions and rewards to evaluate the significance of various primitive behaviors during training. We introduce a causality-aware entropy term that effectively identifies and prioritizes actions with high potential impacts for efficient exploration. Furthermore, to prevent excessive focus on specific primitive behaviors, we analyze the gradient dormancy phenomenon and introduce a dormancy-guided reset mechanism to further enhance the efficacy of our method. Our proposed algorithm, ACE: Off-policy Actor-critic with Causality-aware Entropy regularization, demonstrates a substantial performance advantage across 29 diverse continuous control tasks spanning 7 domains compared to model-free RL baselines, which underscores the effectiveness, versatility, and efficient sample efficiency of our approach. Benchmark results and videos are available at https://ace-rl.github.io/.

📄 PDF Abstract BibTeX arXiv:2402.14528

Code (0)

등록된 구현이 없습니다.

Tasks

continuous-controlContinuous ControlEfficient Exploration

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration

2020-06-02 · Seungyul Han, Youngchul Sung

In this paper, sample-aware policy entropy regularization is proposed to enhance the conventional policy entropy regularization for better exploration. Exploiting the sample distribution obtainable from the replay buffer…

DiversityEfficient Explorationreinforcement-learningReinforcement Learning (RL)

Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement

2018-10-22 · Samuel Neumann, Sungsu Lim, Ajin Joseph, Yangchen Pan 외

Many policy gradient methods are variants of Actor-Critic (AC), where a value function (critic) is learned to facilitate updating the parameterized policy (actor). The update to the actor involves a log-likelihood update…

Policy Gradient MethodsQ-Learning

Off-Policy Actor-Critic in an Ensemble: Achieving Maximum General Entropy and Effective Environment Exploration in Deep Reinforcement Learning

2019-02-14 · Gang Chen, Yiming Peng

We propose a new policy iteration theory as an important extension of soft policy iteration and Soft Actor-Critic (SAC), one of the most efficient model free algorithms for deep reinforcement learning. Supported by the n…

Deep Reinforcement LearningReinforcement Learning

Cautious Actor-Critic

2021-07-12 · Lingwei Zhu, Toshinori Kitamura, Takamitsu Matsubara

The oscillating performance of off-policy learning and persisting errors in the actor-critic (AC) setting call for algorithms that can conservatively learn to suit the stability-critical applications better. In this pape…

continuous-controlContinuous Control

Soft Actor-Critic with Cross-Entropy Policy Optimization

2021-12-21 · Zhenyang Shi, Surya P. N. Singh

Soft Actor-Critic (SAC) is one of the state-of-the-art off-policy reinforcement learning (RL) algorithms that is within the maximum entropy based RL framework. SAC is demonstrated to perform very well in a list of contin…

Reinforcement Learning (RL)