Action Mapping for Reinforcement Learning in Continuous Environments with Constraints
This work addresses sample efficiency and convergence issues in constrained continuous environments for reinforcement learning practitioners, representing an incremental improvement over existing methods.
The paper tackles the challenge of applying deep reinforcement learning to constrained continuous environments by proposing an action mapping strategy that decouples feasible action learning from policy optimization, resulting in significantly improved training performance, especially with imperfect feasibility models.
Deep reinforcement learning (DRL) has had success across various domains, but applying it to environments with constraints remains challenging due to poor sample efficiency and slow convergence. Recent literature explored incorporating model knowledge to mitigate these problems, particularly through the use of models that assess the feasibility of proposed actions. However, integrating feasibility models efficiently into DRL pipelines in environments with continuous action spaces is non-trivial. We propose a novel DRL training strategy utilizing action mapping that leverages feasibility models to streamline the learning process. By decoupling the learning of feasible actions from policy optimization, action mapping allows DRL agents to focus on selecting the optimal action from a reduced feasible action set. We demonstrate through experiments that action mapping significantly improves training performance in constrained environments with continuous action spaces, especially with imperfect feasibility models.