An Integrated Reward Function of End-to-End Deep Reinforcement Learning for the Longitudinal and Lateral Control of Autonomous Vehicles.
Sung-Bean JoPyo-Sang KimHan-You JeongPublished in: VTC Spring (2022)
Keyphrases
- end to end
- autonomous vehicles
- reward function
- reinforcement learning
- reinforcement learning algorithms
- robot control
- markov decision processes
- state space
- path planning
- optimal policy
- structured environments
- control policies
- inverse reinforcement learning
- obstacle avoidance
- multiagent systems
- transition probabilities
- transition model
- function approximation
- state variables
- multiple agents
- multi agent
- markov chain
- decision making
- model free
- control strategies
- autonomous agents
- control policy
- congestion control
- mobile robot
- initially unknown
- action selection
- dynamic systems
- markov random field
- fuzzy logic
- machine learning
- reward signal