Learning Agents With Prioritization and Parameter Noise in Continuous State and Action Space

TL;DR

This paper introduces a prioritized reinforcement learning approach combining DQN and DDPG with parameter noise, achieving improved robustness and performance in continuous state and action space problems like robotics and autonomous vehicles.

Contribution

It presents a novel prioritized method integrating DQN and DDPG with parameter noise, enhancing performance and robustness in continuous RL tasks.

Findings

Outperforms previous methods in continuous RL tasks

Parameter noise improves training robustness

Achieves significant performance gains

Abstract

Among the many variants of RL, an important class of problems is where the state and action spaces are continuous -- autonomous robots, autonomous vehicles, optimal control are all examples of such problems that can lend themselves naturally to reinforcement based algorithms, and have continuous state and action spaces. In this paper, we introduce a prioritized form of a combination of state-of-the-art approaches such as Deep Q-learning (DQN) and Deep Deterministic Policy Gradient (DDPG) to outperform the earlier results for continuous state and action space problems. Our experiments also involve the use of parameter noise during training resulting in more robust deep RL models outperforming the earlier results significantly. We believe these results are a valuable addition for continuous state and action space problems.