Model-based Reinforcement Learning for Parameterized Action Spaces.

Renhao Zhang Haotian Fu Yilin Miao George Konidaris

Published in: CoRR (2024)

Keyphrases

model based reinforcement learning
action space
markov decision processes
state space
reinforcement learning
finite state

optimal policy
dynamic programming
average cost
markov decision problems
partially observable

decision processes
policy iteration
infinite horizon
reward function
machine learning

sufficient conditions
real valued
function approximation
action selection
hidden markov models