REVIEW 1 cited by
Dynamics-aware Embeddings
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
In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL). We propose a forward prediction objective for simultaneously learning embeddings of states and action sequences. These embeddings capture the structure of the environment's dynamics, enabling efficient policy learning. We demonstrate that our action embeddings alone improve the sample efficiency and peak performance of model-free RL on control from low-dimensional states. By combining state and action embeddings, we achieve efficient learning of high-quality policies on goal-conditioned continuous control from pixel observations in only 1-2 million environment steps.
Forward citations
Cited by 1 Pith paper
-
Reinforcement-Learning Portfolio Allocation with Dynamic Embedding of Market Information
DERL, a dynamic-embedding RL framework, beats value/equal-weighted portfolios and an MLP predict-then-optimize baseline on 1993-2022 U.S. large-cap returns, chiefly in high-volatility periods.
Discussion (0). Continue with ORCID to comment.