Penalized Proximal Policy Optimization for Safe Reinforcement Learning.
Linrui ZhangLi ShenLong YangShixiang ChenBo YuanXueqian WangDacheng TaoPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- optimization problems
- least squares
- action selection
- markov decision process
- function approximation
- maximum likelihood
- optimization algorithm
- partially observable environments
- global optimization
- state space
- policy iteration
- policy evaluation
- control policies
- optimization process
- optimization methods
- reinforcement learning algorithms
- control policy
- dynamic programming
- multi agent
- learning algorithm
- evolutionary algorithm
- partially observable markov decision processes
- learning process
- markov decision processes
- function approximators
- rl algorithms
- markov decision problems
- approximate dynamic programming
- reinforcement learning problems
- learning problems