Action Pick-up in Dynamic Action Space Reinforcement Learning.
Jiaqi YeXiaodong LiPangjing WuFeng WangPublished in: CoRR (2023)
Keyphrases
- action space
- reinforcement learning
- state space
- markov decision processes
- state and action spaces
- continuous state
- real valued
- action selection
- state action
- stochastic processes
- control policies
- reinforcement learning methods
- continuous state spaces
- function approximation
- reinforcement learning algorithms
- function approximators
- continuous action
- optimal policy
- dynamic environments
- multi agent
- learning algorithm
- policy iteration
- single agent
- reward function
- heuristic search
- markov decision problems