Timezone: »

Inverse Constrained Reinforcement Learning
Shehryar Malik · Usman Anwar · Alireza Aghasi · Ali Ahmed

Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ Virtual #None

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 is available at: \url{https://github.com/shehryar-malik/icrl}.

Author Information

Shehryar Malik (Information Technology University)
Usman Anwar (Information Technlogy University, Lahore.)
Alireza Aghasi (Georgia State University)
Ali Ahmed (Information Technology University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors