Convergent Policy Optimization for Safe Reinforcement Learning.
Ming YuZhuoran YangMladen KolarZhaoran WangPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- optimization algorithm
- function approximation
- state and action spaces
- reward function
- state space
- action selection
- optimization problems
- markov decision process
- markov decision processes
- optimization process
- machine learning
- policy iteration
- global optimization
- optimization method
- multi agent
- state dependent
- transition model
- average reward
- control policies
- markov decision problems
- partially observable domains
- combinatorial optimization
- partially observable environments
- neural network
- reinforcement learning problems
- learning algorithm
- function approximators
- learning process
- partially observable
- dynamic programming
- simulated annealing
- decision problems