A Primer on Maximum Causal Entropy Inverse Reinforcement Learning

2022/03/22 by Adam Gleave, Gleave, Adam, Sam Toyer +1 · 4 citations
Computer Science · #Reinforcement Learning in Robotics #Evolutionary Algorithms and Applications

paper · pdf · doi:10.48550/arxiv.2203.11409

Abstract

Inverse Reinforcement Learning (IRL) algorithms infer a reward function that explains demonstrations provided by an expert acting in the environment. Maximum Causal Entropy (MCE) IRL is currently the most popular formulation of IRL, with numerous extensions. In this tutorial, we present a compressed derivation of MCE IRL and the key results from contemporary implementations of MCE IRL algorithms. We hope this will serve both as an introductory resource for those new to the field, and as a concise reference for those already familiar with these topics.

Cited by

• Distributional Inverse Reinforcement Learning
• Incoherence in Goal-Conditioned Autoregressive Models
• Learning from Preferences and Mixed Demonstrations in General Settings
• Efficient Reward Identification In Max Entropy Reinforcement Learning with Sparsity and Rank Priors

Related

• Generalized Maximum Causal Entropy for Inverse Reinforcement Learning
• Weighted Maximum Entropy Inverse Reinforcement Learning
• Multi-task Maximum Entropy Inverse Reinforcement Learning
• Maximum Entropy Deep Inverse Reinforcement Learning
• Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch