Non-adversarial Inverse Reinforcement Learning Via Successor Feature Matching

Abstract

In inverse reinforcement learning (IRL), an agent seeks to replicate expert demonstrations through interactions with the environment. Traditionally, IRL is treated as an adversarial game, where an adversary searches over reward models, and a learner optimizes the reward through repeated RL procedures. This game-solving approach is both computationally expensive and difficult to stabilize. In this work, we propose a novel approach to IRL by direct policy optimization: exploiting a linear factorization of the return as the inner product of successor features and a reward vector, we design an IRL algorithm by policy gradient descent on the gap between the learner and expert features. Our non-adversarial method does not require learning a reward function and can be solved seamlessly with existing actor-critic RL algorithms. Remarkably, our approach works in state-only settings without expert action labels, a setting which behavior cloning (BC) cannot solve. Empirical results demonstrate th

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyjain2024non

Related papers

• Inverse Reinforcement Learning Without Reinforcement Learning (2023)0.00
• Basis For Intentions: Efficient Inverse Reinforcement Learning Using Past Experience (2022)0.00
• Psiphi-learning: Reinforcement Learning With Demonstrations Using Successor Features And Inverse Temporal Difference Learning (2021)0.00
• Active Exploration For Inverse Reinforcement Learning (2022)0.00
• Maximum-likelihood Inverse Reinforcement Learning With Finite-time Guarantees (2022)0.00
• Is Inverse Reinforcement Learning Harder Than Standard Reinforcement Learning? A Theoretical Perspective (2023)0.00
• Data-driven Inverse Reinforcement Learning For Expert-learner Zero-sum Games (2023)0.00
• Offline Inverse RL: New Solution Concepts And Provably Efficient Algorithms (2024)0.00