Policy Optimization for Continuous Reinforcement Learning.
Hanyang ZhaoWenpin TangDavid D. YaoPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- optimal policy
- action space
- policy search
- continuous state spaces
- action selection
- optimization algorithm
- state and action spaces
- markov decision process
- reinforcement learning problems
- function approximation
- state space
- global optimization
- optimization process
- learning algorithm
- partially observable
- constrained optimization
- control policies
- multi agent
- approximate dynamic programming
- reinforcement learning algorithms
- markov decision processes
- function approximators
- policy gradient
- partially observable domains
- continuous state and action spaces
- actor critic
- policy evaluation
- markov decision problems
- state action
- continuous domains
- evolution strategy
- optimization methods
- optimization method