Robust Adversarial Reinforcement Learning

TL;DR

This paper introduces Robust Adversarial Reinforcement Learning (RARL), a method where an agent trains against an adversary applying disturbances, leading to improved stability and robustness in various environments.

Contribution

The paper proposes a novel RARL framework that trains agents with an adversarial disturbance, enhancing robustness and transferability of policies in reinforcement learning.

Findings

Improves training stability across environments

Enhances robustness to training and test scenario differences

Outperforms baseline methods even without adversarial disturbance

Abstract

Deep neural networks coupled with fast simulation and improved computation have led to recent successes in the field of reinforcement learning (RL). However, most current RL-based approaches fail to generalize since: (a) the gap between simulation and real world is so large that policy-learning approaches fail to transfer; (b) even if policy learning is done in real world, the data scarcity leads to failed generalization from training to test scenarios (e.g., due to different friction or object masses). Inspired from H-infinity control methods, we note that both modeling errors and differences in training and test scenarios can be viewed as extra forces/disturbances in the system. This paper proposes the idea of robust adversarial reinforcement learning (RARL), where we train an agent to operate in the presence of a destabilizing adversary that applies disturbance forces to the system. The jointly trained adversary is reinforced -- that is, it learns an optimal destabilization policy. We formulate the policy learning as a zero-sum, minimax objective function. Extensive experiments in multiple environments (InvertedPendulum, HalfCheetah, Swimmer, Hopper and Walker2d) conclusively demonstrate that our method (a) improves training stability; (b) is robust to differences in training/test conditions; and c) outperform the baseline even in the absence of the adversary.