Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation

Abstract

The generalization gap in reinforcement learning (RL) has been a significant obstacle that prevents the RL agent from learning general skills and adapting to varying environments. Increasing the generalization capacity of the RL systems can significantly improve their performance on real-world working environments. In this work, we propose a novel policy-aware adversarial data augmentation method to augment the standard policy learning method with automatically generated trajectory data. Different from the commonly used observation transformation based data augmentations, our proposed method adversarially generates new trajectory data based on the policy gradient objective and aims to more effectively increase the RL agent's generalization ability with the policy-aware data augmentation. Moreover, we further deploy a mixup step to integrate the original and generated data to enhance the generalization capacity while mitigating the over-deviation of the adversarial data. We conduct experiments on a number of RL tasks to investigate the generalization performance of the proposed method by comparing it with the standard baselines and the state-of-the-art mixreg approach. The results show our method can generalize well with limited training diversity, and achieve the state-of-the-art generalization test performance.

References in corpus (13)

• mixup: Beyond Empirical Risk Minimization
• Dota 2 with Large Scale Deep Reinforcement Learning
• StarCraft II: A New Challenge for Reinforcement Learning
• Generalizing to Unseen Domains via Adversarial Data Augmentation
• A Closer Look at Memorization in Deep Networks
• Certifying Some Distributional Robustness with Principled Adversarial Training
• Reinforcement Learning with Augmented Data
• A Study on Overfitting in Deep Reinforcement Learning
• Tactics of Adversarial Attack on Deep Reinforcement Learning Agents
• Adversarial Policies: Attacking Deep Reinforcement Learning
• A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning
• Minimax Statistical Learning with Wasserstein Distances
• Improving Generalization in Reinforcement Learning with Mixture Regularization

Cited by in corpus (1)

• A Survey of Zero-shot Generalisation in Deep Reinforcement Learning