A0C: Alpha Zero in Continuous Action Space.
Thomas M. MoerlandJoost BroekensAske PlaatCatholijn M. JonkerPublished in: CoRR (2018)
Keyphrases
- action space
- state space
- markov decision processes
- real valued
- continuous state
- reinforcement learning
- state and action spaces
- continuous state spaces
- stochastic processes
- action selection
- continuous action
- single agent
- data mining
- markov decision process
- heuristic search
- state action
- supervised learning
- dynamic programming
- cooperative