Belief-state RWKV maintains an uncertainty-aware recurrent state for RL policies in partial observability and shows modest gains over standard recurrent baselines in a pilot with observation noise.
Pigdreamer: Privileged information guided world models for safe partially observable reinforcement learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Belief-State RWKV for Reinforcement Learning under Partial Observability
Belief-state RWKV maintains an uncertainty-aware recurrent state for RL policies in partial observability and shows modest gains over standard recurrent baselines in a pilot with observation noise.