Reinforcement learning in multidimensional continuous action spaces.
Jason PazisMichail G. LagoudakisPublished in: ADPRL (2011)
Keyphrases
- action space
- reinforcement learning
- state space
- markov decision processes
- state and action spaces
- continuous state
- real valued
- continuous state spaces
- stochastic processes
- action selection
- state action
- function approximation
- reinforcement learning methods
- control policies
- function approximators
- skill learning
- continuous action
- markov decision process
- reinforcement learning algorithms
- temporal difference
- optimal policy
- single agent
- heuristic search
- markov random field
- learning algorithm
- dynamic programming
- multi agent systems
- policy search
- reinforcement learning problems
- cooperative
- multi agent