Q-chunking improves offline-to-online RL sample efficiency on long-horizon sparse-reward manipulation tasks by applying action chunking to TD learning.
Asynchronous methods for deep reinforce- ment learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2025 2verdicts
UNVERDICTED 2representative citing papers
LUFFY mixes off-policy reasoning traces into RLVR training via Mixed-Policy GRPO and regularized importance sampling, delivering over 6-point gains on math benchmarks and enabling training of weak models where on-policy RLVR fails.
citing papers explorer
-
Reinforcement Learning with Action Chunking
Q-chunking improves offline-to-online RL sample efficiency on long-horizon sparse-reward manipulation tasks by applying action chunking to TD learning.
-
Learning to Reason under Off-Policy Guidance
LUFFY mixes off-policy reasoning traces into RLVR training via Mixed-Policy GRPO and regularized importance sampling, delivering over 6-point gains on math benchmarks and enabling training of weak models where on-policy RLVR fails.