Policy Optimization for Continuous Reinforcement Learning.
Hanyang ZhaoWenpin TangDavid D. YaoPublished in: NeurIPS (2023)
Keyphrases
- reinforcement learning
- action space
- optimal policy
- continuous state spaces
- state space
- optimization algorithm
- policy search
- markov decision process
- markov decision processes
- action selection
- state and action spaces
- approximate dynamic programming
- global optimization
- function approximation
- markov decision problems
- evolution strategy
- actor critic
- policy iteration
- partially observable
- optimization problems
- policy evaluation
- continuous state
- partially observable markov decision processes
- model free
- infinite horizon
- reinforcement learning problems
- transition model
- mobile robot
- learning algorithm
- linear programming
- control policies
- rl algorithms
- dynamical systems
- reinforcement learning algorithms
- reward function
- long run
- optimization process