Login / Signup
A stochastic maximum principle approach for reinforcement learning with parameterized environment.
Richard Archibald
Feng Bao
Jiongmin Yong
Published in:
J. Comput. Phys. (2023)
Keyphrases
</>
reinforcement learning
mobile robot
state space
monte carlo
real time
direct policy search
stochastic approximation
markov decision processes
multi agent environments
exploration strategy
partial knowledge
stochastic processes
temporal difference
function approximation
optimal policy
multi agent
learning algorithm