Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learning
This addresses the challenge of reliable performance in real-world RL tasks for applications requiring safety and robustness, though it is an incremental improvement over existing robust RL methods.
The paper tackles the problem of reinforcement learning agents lacking robustness to unseen worst-case situations by proposing the RH-UCRL algorithm, which achieves near-optimal sample complexity and outperforms other robust deep RL algorithms in adversarial environments.
In real-world tasks, reinforcement learning (RL) agents frequently encounter situations that are not present during training time. To ensure reliable performance, the RL agents need to exhibit robustness against worst-case situations. The robust RL framework addresses this challenge via a worst-case optimization between an agent and an adversary. Previous robust RL algorithms are either sample inefficient, lack robustness guarantees, or do not scale to large problems. We propose the Robust Hallucinated Upper-Confidence RL (RH-UCRL) algorithm to provably solve this problem while attaining near-optimal sample complexity guarantees. RH-UCRL is a model-based reinforcement learning (MBRL) algorithm that effectively distinguishes between epistemic and aleatoric uncertainty and efficiently explores both the agent and adversary decision spaces during policy learning. We scale RH-UCRL to complex tasks via neural networks ensemble models as well as neural network policies. Experimentally, we demonstrate that RH-UCRL outperforms other robust deep RL algorithms in a variety of adversarial environments.