IQ-Learn: Inverse soft-Q Learning for Imitation

Stanford University1
In NeurIPS 2021 (Spotlight)




IQ-Learn reaching human performance on Atari through pure imitation
Showing Pong (Top Left), Breakout (Top Right), Space Invaders (Bottom Left) , QBert (Bottom Right).


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.




Recovering Rewards

Recovering environment rewards on a discrete GridWorld environment with 5 possible actions: up, down, left, right, stay





	title={IQ-Learn: Inverse soft-Q Learning for Imitation},
	author={Divyansh Garg and Shuvam Chakraborty and Chris Cundy and Jiaming Song and Stefano Ermon},
	booktitle={Thirty-Fifth Conference on Neural Information Processing Systems},