REVIEW 3 cited by
Dynamics Generalization via Information Bottleneck in Deep 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
Signed reviews
read the original abstract
Despite the significant progress of deep reinforcement learning (RL) in solving sequential decision making problems, RL agents often overfit to training environments and struggle to adapt to new, unseen environments. This prevents robust applications of RL in real world situations, where system dynamics may deviate wildly from the training settings. In this work, our primary contribution is to propose an information theoretic regularization objective and an annealing-based optimization method to achieve better generalization ability in RL agents. We demonstrate the extreme generalization benefits of our approach in different domains ranging from maze navigation to robotic tasks; for the first time, we show that agents can generalize to test parameters more than 10 standard deviations away from the training parameter distribution. This work provides a principled way to improve generalization in RL by gradually removing information that is redundant for task-solving; it opens doors for the systematic study of generalization from training to extremely different testing settings, focusing on the established connections between information theory and machine learning.
Forward citations
Cited by 3 Pith papers
-
Maximum Total Correlation Reinforcement Learning
A reinforcement learning regularizer that maximizes trajectory-level total correlation produces simpler, more compressible policies that are more robust to perturbations.
-
Generalization Capability for Imitation Learning
The paper argues that imitation learning generalization is governed by representation compression and encoder-data dependence, and that high conditional entropy in actions tightens the bound, but the key new bound is ...
-
TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement Learning
Appending autoencoder-derived trajectory encodings to the state space improves offline RL transfer to new CartPole dynamics compared with BCQ, though the effect is small in some environments.
Discussion (0). Continue with ORCID to comment.