Addressing High-dimensional Continuous Action Space via Decomposed Discrete Policy-Critic

Yechen Zhang, Jian Sun, Gang Wang, Jie Chen

Keywords: reinforcement learning, continuous control, actor-critic, decomposed policy, discretized action

Abstract: Reinforcement learning (RL) methods for discrete action spaces like DQNs are being widely used in tasks such as Atari games. However, they encounter difficulties when addressing continuous control tasks, since discretizing continuous action space incurs the curse-of-dimensionality. To tackle continuous control tasks via discretized actions, we propose a decomposed discrete policy-critic (D2PC) architecture, which was inspired by multi-agent RL (MARL) and associates with each action dimension a discrete policy, while leveraging a single critic network to provide a shared evaluation. Building on D2PC, we advocate soft stochastic D2PC (SD2PC) and deterministic D2PC (D3PC) methods with a discrete stochastic or deterministic policy, which show comparable or superior training performances relative to even continuous actor-critic methods. Additionally, we design a mechanism that allows D3PC to interact with continuous actor-critic methods, contributing to the Q-policy-critic (QPC) algorithm, which inherits the training efficiency of discrete RL and the near-optimal final performance of continuous RL algorithms. Substantial experimental results on several continuous benchmark tasks validate our claims.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics)