Login / Signup
Discovering Diverse Nearly Optimal Policies withSuccessor Features.
Tom Zahavy
Brendan O'Donoghue
André Barreto
Volodymyr Mnih
Sebastian Flennerhag
Satinder Singh
Published in:
CoRR (2021)
Keyphrases
</>
optimal policy
markov decision processes
reinforcement learning
decision problems
finite state
long run
sufficient conditions
average reward
finite horizon
state space
multistage
search algorithm
infinite horizon
dynamic programming
multi agent
objective function
state dependent
learning algorithm