conftrace_

fitted value iteration

5 papers

Explore in graph

Also known as

FVI

Co-occurring keywords

bellman residual (16) markov decision process (790) function approximation (319) reinforcement learning (4352) continuous state space (24) ecols algorithm (1) second-order optimization (93) robust markov decision processes (3) state aggregation (9) linear approximation (19)

Papers

Krylov–Bellman boosting: Super-linear policy evaluation in general state spaces AISTATS 2023
Value Iteration in Continuous Actions, States and Time ICML 2021
RAAM: The Benefits of Robustness in Approximating Aggregated MDPs in Reinforcement Learning NIPS 2014
Convergent Fitted Value Iteration with Linear Function Approximation NIPS 2011
Finite-Time Bounds for Fitted Value Iteration JMLR 2008