Quantitative and Qualitative Evaluation of Reinforcement Learning Policies for Autonomous Vehicles.
Laura FerrarottiMassimiliano LucaGabriele SantinGiorgio PreviatiGianpiero MastinuElena CampiLorenzo UccelloAntonino AlbanesePraveen ZalayaAlessandro RoccasalvaBruno LepriPublished in: CoRR (2023)
Keyphrases
- autonomous vehicles
- reinforcement learning
- optimal policy
- robot control
- policy search
- path planning
- structured environments
- markov decision process
- obstacle avoidance
- reward function
- partially observable markov decision processes
- route planning
- function approximation
- state space
- control policy
- reinforcement learning algorithms
- autonomous agents
- markov decision processes
- multiagent systems
- markov decision problems
- fitted q iteration
- dynamic programming
- mobile robot
- model free
- multi agent
- real time
- traffic light
- fuzzy sets
- multi objective
- learning algorithm