Generative Adversarial Imitation Learning

Abstract

Consider learning a policy from example expert behavior, without interaction with the expert or access to reinforcement signal. One approach is to recover the expert's cost function with inverse reinforcement learning, then extract a policy from that cost function with reinforcement learning. This approach is indirect and can be slow. We propose a new general framework for directly extracting a policy from data, as if it were obtained by reinforcement learning following inverse reinforcement learning. We show that a certain instantiation of our framework draws an analogy between imitation learning and generative adversarial networks, from which we derive a model-free imitation learning algorithm that obtains significant performance gains over existing model-free methods in imitating complex behaviors in large, high-dimensional environments.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyho2016generative

Related papers

• Adversarial Soft Advantage Fitting: Imitation Learning Without Policy Optimization (2020)0.00
• Non-adversarial Imitation Learning And Its Connections To Adversarial Methods (2020)0.00
• A New Framework For Query Efficient Active Imitation Learning (2019)0.00
• Adversarial Imitation Learning Via Random Search (2020)7.16
• Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning (2020)7.81
• Online Adaptation For Enhancing Imitation Learning Policies (2024)0.00
• Fully General Online Imitation Learning (2021)0.00
• Imitating Opponent To Win: Adversarial Policy Imitation Learning In Two-player Competitive Games (2022)0.00