DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.
Journal of artificial intelligence research , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Odysseus adapts PPO with a turn-level critic and leverages pretrained VLM action priors to train agents achieving at least 3x average game progress over frontier models in long-horizon Super Mario Land.
Higher-resolution observations with global-average-pooling encoders improve RL performance and generalization by enabling more localized visual attention, yielding up to 28% gains over standard Impala encoders.
citing papers explorer
-
Discrete Flow Matching for Offline-to-Online Reinforcement Learning
DRIFT enables stable offline-to-online fine-tuning of CTMC policies in discrete RL via advantage-weighted discrete flow matching, path-space regularization, and candidate-set approximation.
-
Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning
Odysseus adapts PPO with a turn-level critic and leverages pretrained VLM action priors to train agents achieving at least 3x average game progress over frontier models in long-horizon Super Mario Land.
-
Higher Resolution, Better Generalization: Unlocking Visual Scaling in Deep Reinforcement Learning
Higher-resolution observations with global-average-pooling encoders improve RL performance and generalization by enabling more localized visual attention, yielding up to 28% gains over standard Impala encoders.