Generalising Discrete Action Spaces with Conditional Action Trees.

Christopher Bamford Alvaro Ovalle

Published in: CoG (2021)

Keyphrases

continuous action
action space
continuous state
state space
policy search
continuous state spaces
real valued
markov decision processes
reinforcement learning
control policies
action selection
state action
stochastic processes
skill learning
single agent
markov chain
hidden markov models