Lane-Merging Using Policy-based Reinforcement Learning and Post-Optimization.
Patrick HartLeonard RychlyAlois C. KnollPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- partially observable
- global optimization
- state space
- reinforcement learning algorithms
- optimization algorithm
- markov decision processes
- approximate dynamic programming
- constrained optimization
- control policies
- optimization problems
- policy gradient
- control policy
- decision problems
- function approximation
- detection algorithm
- particle swarm optimization
- dynamic programming
- partially observable environments
- reinforcement learning problems
- neural network
- policy iteration
- action selection
- model free
- optimization process
- optimization method
- multi agent
- learning algorithm