Diverse Policy Optimization for Structured Action Space.
Wenhao LiBaoxiang WangShanchao YangHongyuan ZhaPublished in: CoRR (2023)
Keyphrases
- action space
- state space
- state and action spaces
- markov decision processes
- real valued
- control policies
- reinforcement learning
- continuous state
- continuous state spaces
- optimal policy
- stochastic processes
- action selection
- function approximators
- markov decision problems
- markov decision process
- state action
- cooperative
- single agent
- higher order
- reinforcement learning methods
- image segmentation