Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints
It addresses the problem of ensuring feasible and safe actions in real-world robotics systems for researchers and practitioners, though it is incremental as it focuses on benchmarking rather than introducing a new method.
This study benchmarks actor-critic deep reinforcement learning algorithms for robotics control with action constraints, evaluating existing methods and novel variants across multiple environments to provide the first in-depth perspective, revealing insights such as the effectiveness of a straightforward baseline approach.
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 straightforward baseline approach. The benchmark problems and associated code utilized in our experiments are made available online at github.com/omron-sinicx/action-constrained-RL-benchmark for further research and development.