Constrained Dirichlet Distribution Policy: Guarantee Zero Constraint Violation Reinforcement Learning for Continuous Robotic Control

Learning-based controllers show promising performances in robotic control tasks. However, they still present potential safety risks due to the difficulty in ensuring satisfaction of complex action constraints. We propose a novel action-constrained reinforcement learning method, which transforms the constrained action space into its dual space and uses Dirichlet distribution policy to guarantee strict constraint satisfaction as well as randomized exploration. We validate the proposed method in benchmark environments and in a real quadruped locomotion task. Our method outperforms other baselines with higher reward and faster inference speed. Results of the real robot experiments demonstrate the effectiveness and potential application of our method.