Safe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimization.
Lu WenJingliang DuanShengbo Eben LiShaobing XuHuei PengPublished in: CoRR (2020)
Keyphrases
- autonomous vehicles
- reinforcement learning
- optimal policy
- concave convex procedure
- structured environments
- policy search
- obstacle avoidance
- robot control
- path planning
- optimization algorithm
- action selection
- markov decision process
- function approximation
- real time
- reward function
- markov decision processes
- action space
- multi agent
- function approximators
- autonomous robots
- global optimization
- state space
- control policy
- policy gradient
- decision making
- machine learning