Energy-Based Imitation Learning

By Minghuan Liu, Tairan He, Minkai Xu, Weinan Zhang. 2020

55 citations recorded by the source corpus.

We tackle a common scenario in imitation learning (IL), where agents try to recover the optimal policy from expert demonstrations without further access to the expert or environment reward signals. Except the simple Behavior Cloning (BC) that adopts supervised learning followed by the problem of compounding error, previous solutions like inverse reinforcement learning (IRL) and recent generative adversarial methods involve a bi-level or alternating optimization for updating the reward function and the policy, suffering from high computational cost and training instability. Inspired by recent progress in energy-based model (EBM), in this paper, we propose a simplified IL framework named Energy-Based Imitation Learning (EBIL). Instead of updating the reward and policy iteratively, EBIL breaks out of the traditional IRL paradigm by a simple and flexible two-stage solution: first estimating the expert energy as the surrogate reward function through score matching, then utilizing such a reward for learning the policy by reinforcement learning algorithms. EBIL combines the idea of both EBM and occupancy measure matching, and via theoretic analysis we reveal that EBIL and Max-Entropy IRL (MaxEnt IRL) approaches are two sides of the same coin, and thus EBIL could be an alternative of adversarial IRL methods. Extensive experiments on qualitative and quantitative evaluations indicate that EBIL is able to recover meaningful and interpretative reward signals while achieving effective and comparable performance against existing algorithms on IL benchmarks.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Implicit Behavioral Cloning (2021, methodology): “Other recent work [14] uses EBMs in a model-based planning framework, or 230 uses EBMs in imitation learning [48] but with an on-policy algorithm.”
Behavior Transformers: Cloning k modes with one stone (2022, background): “Finally, a class of algorithms, most notably [50, 25, 43, 58] do not directly learn a generative model but instead learn energy based models.”
Vision-Language Foundation Models as Effective Robot Imitators (2023, background): “Imitation learning (Pomerleau, 1988; Zhang et al., 2018; Liu et al., 2020; Jang et al., 2022) allows the agent to mimic the manipulation plans from instruction-labeled expert play data , where D is the number of trajectories, l is the language instruction, and τ = { ( o t , a t ) } contains…”