Inverse Constrained Reinforcement Learning
This work is significant for enabling safer real-world deployment of reinforcement learning agents by learning implicit constraints, which is a problem for practitioners deploying RL.
The paper addresses the challenge of specifying mathematical constraints for safe reinforcement learning by proposing a framework to learn constraints from demonstrations of a constraint-abiding agent's behavior. The framework successfully learns the most likely constraints and demonstrates their transferability to new agents with different morphologies or reward functions.
In real world settings, numerous constraints are present which are hard to specify mathematically. However, for the real world deployment of reinforcement learning (RL), it is critical that RL agents are aware of these constraints, so that they can act safely. In this work, we consider the problem of learning constraints from demonstrations of a constraint-abiding agent's behavior. We experimentally validate our approach and show that our framework can successfully learn the most likely constraints that the agent respects. We further show that these learned constraints are \textit{transferable} to new agents that may have different morphologies and/or reward functions. Previous works in this regard have either mainly been restricted to tabular (discrete) settings, specific types of constraints or assume the environment's transition dynamics. In contrast, our framework is able to learn arbitrary \textit{Markovian} constraints in high-dimensions in a completely model-free setting. The code can be found it: \url{https://github.com/shehryar-malik/icrl}.