Balanced reward-inspired reinforcement learning for autonomous vehicle racing.
Zhen TianDezong ZhaoZhihao LinDavid FlynnWenjing ZhaoDaxin TianPublished in: L4DC (2024)
Keyphrases
- reinforcement learning
- autonomous vehicles
- robot control
- path planning
- obstacle avoidance
- eligibility traces
- function approximation
- state space
- temporal difference
- mobile robot
- optimal policy
- multiagent systems
- reinforcement learning algorithms
- lane detection
- model free
- map building
- markov decision processes
- multi agent
- learning algorithm
- policy gradient
- robot motion
- machine learning
- average reward
- autonomous agents
- real time
- learning agent
- control strategies
- long range
- dynamic programming
- partially observable environments