Active Exploration Deep Reinforcement Learning for Continuous Action Space with Forward Prediction.
Dongfang ZhaoXu HuanshiZhang XunPublished in: Int. J. Comput. Intell. Syst. (2024)
Keyphrases
- action space
- reinforcement learning
- active exploration
- state space
- markov decision processes
- state and action spaces
- real valued
- continuous state
- continuous state spaces
- action selection
- stochastic processes
- reinforcement learning methods
- continuous action
- state action
- function approximators
- single agent
- model free
- dynamic programming
- markov decision process
- function approximation
- markov decision problems
- learning process
- small sample
- prediction model
- partially observable
- optimal control
- sample size
- supervised learning
- case study