Using Monte Carlo Tree Search as a Demonstrator within Asynchronous Deep RL.
Bilal KartalPablo Hernandez-LealMatthew E. TaylorPublished in: CoRR (2018)
Keyphrases
- monte carlo tree search
- bayesian reinforcement learning
- monte carlo
- reinforcement learning
- reinforcement learning methods
- temporal difference
- tree search algorithm
- temporal difference learning
- evaluation function
- optimal policy
- function approximation
- reinforcement learning algorithms
- monte carlo search
- dynamical systems
- model free
- action selection
- state space
- action space
- multi agent
- game playing
- policy iteration
- long run
- learning algorithm
- markov chain
- supervised learning
- objective function
- decision making