IQ-Learn: Inverse soft-Q Learning for Imitation

Abstract

In many sequential decision-making problems (e.g., robotics control, game playing, sequential prediction), human or expert data is available containing useful information about the task. However, imitation learning (IL) from a small amount of expert data can be challenging in high-dimensional environments with complex dynamics. Behavioral cloning is a simple method that is widely used due to its simplicity of implementation and stable convergence but doesn't utilize any information involving the environment's dynamics. Many existing methods that exploit dynamics information are difficult to train in practice due to an adversarial optimization process over reward and policy approximators or biased, high variance gradient estimators. We introduce a method for dynamics-aware IL which avoids adversarial training by learning a single Q-function, implicitly representing both reward and policy. On standard benchmarks, the implicitly learned rewards show a high positive correlation with the ground-truth rewards, illustrating our method can also be used for inverse reinforcement learning (IRL). Our method, Inverse soft-Q learning (IQ-Learn) obtains state-of-the-art results in offline and online imitation learning settings, significantly outperforming existing methods both in the number of required environment interactions and scalability in high-dimensional spaces, often by more than 3x.

Spotlight in NeurIPS 2021. Winner of '21 MineRL BASALT Challenge. Website: https://div99.github.io/IQ-Learn

References in corpus (9)

• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Spectral Normalization for Generative Adversarial Networks
• Reinforcement Learning with Deep Energy-Based Policies
• Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning
• SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards
• Meta-Inverse Reinforcement Learning with Probabilistic Context Variables
• Imitation Learning via Off-Policy Distribution Matching
• Non-Adversarial Imitation Learning and its Connections to Adversarial Methods
• A Critique of Strictly Batch Imitation Learning