REVIEW 4 cited by
Optimal Transport for Offline 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
With the advent of large datasets, offline reinforcement learning (RL) is a promising framework for learning good decision-making policies without the need to interact with the real environment. However, offline RL requires the dataset to be reward-annotated, which presents practical challenges when reward engineering is difficult or when obtaining reward annotations is labor-intensive. In this paper, we introduce Optimal Transport Reward labeling (OTR), an algorithm that assigns rewards to offline trajectories, with a few high-quality demonstrations. OTR's key idea is to use optimal transport to compute an optimal alignment between an unlabeled trajectory in the dataset and an expert demonstration to obtain a similarity measure that can be interpreted as a reward, which can then be used by an offline RL algorithm to learn the policy. OTR is easy to implement and computationally efficient. On D4RL benchmarks, we show that OTR with a single demonstration can consistently match the performance of offline RL with ground-truth rewards.
Forward citations
Cited by 4 Pith papers
-
PINS: Proximal Iterations with Sparse Newton and Sinkhorn for Optimal Transport
PINS combines an outer proximal-point loop over shifted entropic OT problems with inner Sinkhorn warm-up and sparse-Newton refinement to reach unregularized OT solutions with global convergence and lower error than Si...
-
Re:Frame -- Retrieving Experience From Associative Memory
A plug-in that retrieves expert actions from a small associative memory buffer improves offline Decision Transformer performance on three of four D4RL MuJoCo tasks, with gains up to 10.7 points.
-
WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception
WorldWeaver reduces temporal drift in long-horizon video generation by jointly modeling RGB and depth perceptual conditions with segmented noise scheduling.
-
Foundation Models for Cross-Domain EEG Analysis Application: A Survey
A survey that organizes EEG foundation-model research into five output-modality categories: native EEG, text, vision, audio, and multimodal fusion, with a claim to be the first such comprehensive taxonomy.
Discussion (0). Sign in to comment.