ACH lets RL policies dynamically pick action chunk lengths by jointly estimating Q-values for all candidate lengths via a single Transformer pass.
Chunk-guided q-learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
ACSAC adaptively selects action chunk sizes via a causal Transformer Q-network in actor-critic RL, proves the Bellman operator is a contraction, and reports state-of-the-art results on long-horizon manipulation tasks.
citing papers explorer
-
Adaptive Action Chunking via Multi-Chunk Q Value Estimation
ACH lets RL policies dynamically pick action chunk lengths by jointly estimating Q-values for all candidate lengths via a single Transformer pass.
-
ACSAC: Adaptive Chunk Size Actor-Critic with Causal Transformer Q-Network
ACSAC adaptively selects action chunk sizes via a causal Transformer Q-network in actor-critic RL, proves the Bellman operator is a contraction, and reports state-of-the-art results on long-horizon manipulation tasks.