An Overview of the Action Space for Deep Reinforcement Learning.
Jie ZhuFengge WuJunsuo ZhaoPublished in: ACAI (2021)
Keyphrases
- action space
- reinforcement learning
- state space
- state and action spaces
- markov decision processes
- continuous state
- real valued
- reinforcement learning methods
- action selection
- control policies
- reinforcement learning algorithms
- continuous state spaces
- machine learning
- markov decision process
- state action
- stochastic processes
- markov decision problems
- multi agent
- dynamic programming
- learning algorithm
- model free
- function approximators
- function approximation
- transfer learning
- initial state
- optimal policy
- computational complexity
- search algorithm
- data mining