Linear Reinforcement Learning with Ball Structure Action Space.
Zeyu JiaRandy JiaDhruv MadekaDean P. FosterPublished in: CoRR (2022)
Keyphrases
- action space
- reinforcement learning
- state space
- markov decision processes
- state and action spaces
- function approximators
- real valued
- continuous state
- hidden markov models
- action selection
- control policies
- reinforcement learning algorithms
- stochastic processes
- model free
- function approximation
- state action
- reinforcement learning methods
- optimal policy
- continuous state spaces
- higher order