Login / Signup
Confident Approximate Policy Iteration for Efficient Local Planning in $q^\pi$-realizable MDPs.
Gellért Weisz
András György
Tadashi Kozuno
Csaba Szepesvári
Published in:
NeurIPS (2022)
Keyphrases
</>
policy iteration
markov decision processes
markov decision problems
state space
reinforcement learning
planning problems
multi agent
approximate policy iteration
cooperative
heuristic search
domain independent