Relational hidden states anchored to environment states are what let a model-free RL agent plan, and a free-slot control without that anchoring shows no planning signatures.
Title resolution pending
1 Pith paper cite this work, alongside 340 external citations. Polarity classification is still indexing.
1
Pith paper citing it
340
external citations · OpenAlex
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Planning as Emergent Behavior in Reinforcement Learning with Relational Hidden States
Relational hidden states anchored to environment states are what let a model-free RL agent plan, and a free-slot control without that anchoring shows no planning signatures.