Lane-Merging Using Policy-based Reinforcement Learning and Post-Optimization.
Patrick HartLeonard RychlyAlois C. KnollPublished in: ITSC (2019)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- action selection
- optimization problems
- optimization algorithm
- markov decision process
- learning algorithm
- state space
- markov decision processes
- policy iteration
- partially observable environments
- reinforcement learning problems
- control policies
- function approximators
- reinforcement learning algorithms
- constrained optimization
- function approximation
- reinforcement learning methods
- global optimization
- control policy
- optimization process
- temporal difference
- optimal control
- action space
- convergence rate
- reward function
- model free
- markov decision problems
- policy gradient
- policy evaluation
- actor critic
- transition model
- detection algorithm
- inverse reinforcement learning
- dynamic programming
- machine learning