Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learning
This addresses scalability and explainability issues in RL for domains requiring efficient and interpretable simulations, representing a novel method for a known bottleneck.
The paper tackles the limitations of reinforcement learning in scalability, explainability, and Markovian assumptions by proposing a semantic proxy for simulation based on temporal annotated logic, achieving up to three orders of magnitude speed-up while preserving policy quality and enabling modeling of non-Markovian dynamics with explainable traces.
Recent advances in reinforcement learning (RL) have shown much promise across a variety of applications. However, issues such as scalability, explainability, and Markovian assumptions limit its applicability in certain domains. We observe that many of these shortcomings emanate from the simulator as opposed to the RL training algorithms themselves. As such, we propose a semantic proxy for simulation based on a temporal extension to annotated logic. In comparison with two high-fidelity simulators, we show up to three orders of magnitude speed-up while preserving the quality of policy learned. In addition, we show the ability to model and leverage non-Markovian dynamics and instantaneous actions while providing an explainable trace describing the outcomes of the agent actions.