Diverse Policy Optimization for Structured Action Space.
Wenhao LiBaoxiang WangShanchao YangHongyuan ZhaPublished in: AAMAS (2023)
Keyphrases
- action space
- state space
- markov decision processes
- reinforcement learning
- state and action spaces
- control policies
- real valued
- stochastic processes
- action selection
- state action
- continuous state spaces
- optimal policy
- continuous state
- markov decision process
- heuristic search
- machine learning
- single agent
- path planning
- least squares
- function approximators
- multi agent systems
- decision making