Diversity Actor-Critic: Sample-Aware Entropy Regularization for Sample-Efficient Exploration
arXiv:2006.01419
Abstract
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, the proposed sample-aware entropy regularization maximizes the entropy of the weighted sum of the policy action distribution and the sample action distribution from the replay buffer for sample-efficient exploration. A practical algorithm named diversity actor-critic (DAC) is developed by applying policy iteration to the objective function with the proposed sample-aware entropy regularization. Numerical results show that DAC significantly outperforms existing recent algorithms for reinforcement learning.
Accepted to Proceedings of the 38th International Conference on Machine Learning
References in corpus (7)
- Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
- Parameter Space Noise for Exploration
- Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning
- Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic
- Provably Efficient Maximum Entropy Exploration
- Tsallis Reinforcement Learning: A Unified Framework for Maximum Entropy Reinforcement Learning
- Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning
Cited by in corpus (5)
- Adversarially Guided Actor-Critic
- A Reinforcement Learning Formulation of the Lyapunov Optimization: Application to Edge Computing Systems with Queue Stability
- A Max-Min Entropy Framework for Reinforcement Learning
- Learning Diverse Policies with Soft Self-Generated Guidance
- PAC-Bayesian Soft Actor-Critic Learning