Almanac
paper

Generalization in offline RL: The structure is more important than the amount of pessimism

paperactiveprovisionalgeneralization-in-offline-rl-the-structure-is-more-important-than-the-amount-of-pessimism-e0cb1ac9·1 events·first seen 14h ago

Aliases: Generalization in offline RL: The structure is more important than the amount of pessimism

Co-occurring entities

More like this (12)

Recent events (1)

4arXiv · cs.AI·14h ago·source ↗

Offline RL generalization depends on symmetry structure of pessimism, not its magnitude

A new arXiv preprint argues that successful generalization in offline reinforcement learning depends on whether the pessimistic value function respects the symmetries of the optimal solution, not on the degree of pessimism applied. The authors prove that a mildly pessimistic but non-symmetric value function can generalize worse than an overly pessimistic symmetric one, with implications for how data augmentation should be applied. They validate the theory empirically using IQL and CQL on a rotationally symmetric reacher environment, recommending a consistency loss during policy extraction over augmented dataset training.