REVIEW 2 cited by
A Behavior Regularized Implicit Policy for Offline Reinforcement 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
Offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. The lack of environmental interactions makes the policy training vulnerable to state-action pairs far from the training dataset and prone to missing rewarding actions. For training more effective agents, we propose a framework that supports learning a flexible yet well-regularized fully-implicit policy. We further propose a simple modification to the classical policy-matching methods for regularizing with respect to the dual form of the Jensen--Shannon divergence and the integral probability metrics. We theoretically show the correctness of the policy-matching approach, and the correctness and a good finite-sample property of our modification. An effective instantiation of our framework through the GAN structure is provided, together with techniques to explicitly smooth the state-action mapping for robust generalization beyond the static dataset. Extensive experiments and ablation study on the D4RL benchmark validate our framework and the effectiveness of our algorithmic designs.
Forward citations
Cited by 2 Pith papers
-
Drift Q-Learning
DriftQL is a single-pass offline RL algorithm using drift regularization that outperforms diffusion and flow policies on standard benchmarks.
-
Wavelet Fourier Diffuser: Frequency-Aware Diffusion Model for Reinforcement Learning
A wavelet-Fourier conditioning scheme for trajectory diffusion improves offline RL returns on most D4RL tasks by modeling low- and high-frequency components separately.
Discussion (0). Sign in to comment.