SoftDICE for Imitation Learning: Rethinking Off-policy Distribution Matching

by   Mingfei Sun, et al.

We present SoftDICE, which achieves state-of-the-art performance for imitation learning. SoftDICE fixes several key problems in ValueDICE, an off-policy distribution matching approach for sample-efficient imitation learning. Specifically, the objective of ValueDICE contains logarithms and exponentials of expectations, for which the mini-batch gradient estimate is always biased. Second, ValueDICE regularizes the objective with replay buffer samples when expert demonstrations are limited in number, which however changes the original distribution matching problem. Third, the re-parametrization trick used to derive the off-policy objective relies on an implicit assumption that rarely holds in training. We leverage a novel formulation of distribution matching and consider an entropy-regularized off-policy objective, which yields a completely offline algorithm called SoftDICE. Our empirical results show that SoftDICE recovers the expert policy with only one demonstration trajectory and no further on-policy/off-policy samples. SoftDICE also stably outperforms ValueDICE and other baselines in terms of sample efficiency on Mujoco benchmark tasks.


page 8

page 12


CEIL: Generalized Contextual Imitation Learning

In this paper, we present ContExtual Imitation Learning (CEIL), a genera...

Imitation Learning via Off-Policy Distribution Matching

When performing imitation learning from expert demonstrations, distribut...

Deterministic and Discriminative Imitation (D2-Imitation): Revisiting Adversarial Imitation for Sample Efficiency

Sample efficiency is crucial for imitation learning methods to be applic...

A Coupled Flow Approach to Imitation Learning

In reinforcement learning and imitation learning, an object of central i...

Minimax Optimal Online Imitation Learning via Replay Estimation

Online imitation learning is the problem of how best to mimic expert dem...

SMODICE: Versatile Offline Imitation Learning via State Occupancy Matching

We propose State Matching Offline DIstribution Correction Estimation (SM...

Strictly Batch Imitation Learning by Energy-based Distribution Matching

Consider learning a policy purely on the basis of demonstrated behavior—...

Please sign up or login with your details

Forgot password? Click here to reset