A comparison of action selection methods for implicit policy method reinforcement learning in continuous action-space.
Barry D. NicholsPublished in: IJCNN (2016)
Keyphrases
- action space
- action selection
- continuous state spaces
- reinforcement learning
- continuous state and action spaces
- function approximators
- state space
- markov decision processes
- control problems
- state action
- function approximation
- temporal difference
- dynamic programming
- reinforcement learning methods
- continuous state
- model free
- robot soccer
- state and action spaces
- basal ganglia
- policy search
- markov decision process
- continuous action
- computational complexity
- multi agent systems
- objective function