Optimistic critic estimates (mean or max over two Q functions) counteract value underestimation and recover most of the performance lost by shrinking the actor in SAC and DrQ.
Unbiased Asymmetric Reinforcement Learning under Partial Observability
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Optimistic critics can empower small actors
Optimistic critic estimates (mean or max over two Q functions) counteract value underestimation and recover most of the performance lost by shrinking the actor in SAC and DrQ.