Login / Signup
Replay Memory as An Empirical MDP: Combining Conservative Estimation with Experience Replay.
Hongming Zhang
Chenjun Xiao
Han Wang
Jun Jin
Bo Xu
Martin Müller
Published in:
ICLR (2023)
Keyphrases
</>
memory usage
estimation accuracy
reinforcement learning
parameter estimation
markov decision processes
memory requirements
density estimation
random access
case study
estimation error
finite state
accurate estimation
computing power
limited memory