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