Policy Transfer via Enhanced Action Space.
Zheng ZhangQingrui ZhangBo ZhuXiaohan WangTianjiang HuPublished in: CoRR (2022)
Keyphrases
- action space
- state space
- state and action spaces
- markov decision processes
- real valued
- reinforcement learning
- control policies
- stochastic processes
- continuous state
- continuous state spaces
- action selection
- markov decision process
- state action
- markov decision problems
- optimal policy
- single agent
- dynamic programming
- transfer learning
- function approximators
- multi agent systems
- reinforcement learning methods
- markov chain
- reinforcement learning algorithms
- state variables
- cooperative
- domain independent
- decision making