REVIEW 2 cited by
State Alignment-based Imitation Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Consider an imitation learning problem that the imitator and the expert have different dynamics models. Most of the current imitation learning methods fail because they focus on imitating actions. We propose a novel state alignment-based imitation learning method to train the imitator to follow the state sequences in expert demonstrations as much as possible. The state alignment comes from both local and global perspectives and we combine them into a reinforcement learning framework by a regularized policy update objective. We show the superiority of our method on standard imitation learning settings and imitation learning settings where the expert and imitator have different dynamics models.
Forward citations
Cited by 2 Pith papers
-
Action-Constrained Imitation Learning
DTWIL creates a surrogate demonstration set by aligning expert and constrained state trajectories through model predictive control and dynamic time warping, then trains an imitator on it.
-
Mixture of Autoencoder Experts Guidance using Unlabeled and Incomplete Data for Exploration in Reinforcement Learning
MoE-GUIDE guides RL exploration by rewarding states that a mixture of autoencoders, trained on sparse state-only expert demonstrations, considers similar to expert data.
Discussion (0). Continue with ORCID to comment.