Reinforcement Learning in Large Discrete Action Spaces.
Gabriel Dulac-ArnoldRichard EvansPeter SunehagBen CoppinPublished in: CoRR (2015)
Keyphrases
- action space
- reinforcement learning
- continuous state
- continuous state spaces
- continuous action
- state space
- state and action spaces
- markov decision processes
- policy search
- real valued
- stochastic processes
- control policies
- action selection
- reinforcement learning methods
- function approximation
- robot navigation
- reinforcement learning algorithms
- function approximators
- state action
- skill learning
- reinforcement learning problems
- multi agent
- probability distribution
- machine learning
- dynamic programming
- learning algorithm
- markov decision process
- control problems
- finite state
- parameter estimation
- markov decision problems
- search algorithm
- cooperative
- heuristic search
- decision making