Login / Signup
Bounded real-time dynamic programming: RTDP with monotone upper bounds and performance guarantees.
H. Brendan McMahan
Maxim Likhachev
Geoffrey J. Gordon
Published in:
ICML (2005)
Keyphrases
</>
upper bound
real time dynamic programming
markov decision processes
lower bound
state space
markov decision problems
branch and bound
computational complexity
dynamic programming
reinforcement learning
linear programming
optimal policy
finite state
reward function
initial state