Evaluation Results of Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints

This study presents a benchmark for evaluating action-constrained reinforcement learning (RL) algorithms. In action-constrained RL, each action taken by the learning system must comply with certain constraints. These constraints are crucial for ensuring the feasibility and safety of actions in real-world systems. We evaluate existing algorithms and their novel variants across multiple robotics control environments, encompassing multiple action constraint types. Our evaluation provides the first in-depth perspective of the field, revealing surprising insights, including the effectiveness of a straight- forward baseline approach. The benchmark problems and as- sociated code utilized in our experiments are made avail- able online at github.com/omron-sinicx/action-constrained-RL- benchmark for further research and development.