Introduces a new Q-function definition for continuous-time RL and convergent off-policy algorithms under linear function approximation in model-based and model-free settings.
arXiv preprint arXiv:2112.10264 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PhiBE-Q-Learning: Bridging Off-Policy Reinforcement Learning and Continuous-Time Control
Introduces a new Q-function definition for continuous-time RL and convergent off-policy algorithms under linear function approximation in model-based and model-free settings.