Regularized agent-state-based Q-learning converges almost surely to the fixed point of a regularized MDP induced by the behavioral policy.
Optimal control of Markov processes with incomplete state information I,
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
support 1representative citing papers
citing papers explorer
-
Convergence of regularized agent-state-based Q-learning in POMDPs
Regularized agent-state-based Q-learning converges almost surely to the fixed point of a regularized MDP induced by the behavioral policy.