Evolving Constrained Reinforcement Learning Policy.
Chengpeng HuJiyuan PeiJialin LiuXin YaoPublished in: IJCNN (2023)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- action selection
- partially observable environments
- action space
- control policies
- markov decision problems
- markov decision processes
- policy iteration
- policy evaluation
- reward function
- state and action spaces
- control policy
- state space
- model free
- reinforcement learning problems
- policy gradient
- model free reinforcement learning
- function approximators
- dynamic programming
- approximate dynamic programming
- decision problems
- temporal difference
- reinforcement learning algorithms
- partially observable domains
- partially observable markov decision processes
- approximate policy iteration
- average reward
- actor critic
- partially observable
- function approximation
- rl algorithms
- state action
- infinite horizon
- long run
- policy gradient methods
- agent learns
- asymptotically optimal
- state dependent
- machine learning
- control problems
- continuous state
- reinforcement learning methods
- least squares
- inverse reinforcement learning
- optimal control
- multi agent