Advanced planning for autonomous vehicles using reinforcement learning and deep inverse reinforcement learning.
Changxi YouJianbo LuDimitar P. FilevPanagiotis TsiotrasPublished in: Robotics Auton. Syst. (2019)
Keyphrases
- inverse reinforcement learning
- autonomous vehicles
- partially observable environments
- reinforcement learning
- reward function
- partially observable
- temporal difference
- robot control
- action selection
- obstacle avoidance
- path planning
- reinforcement learning algorithms
- preference elicitation
- markov decision processes
- motion planning
- partially observable markov decision processes
- partial observability
- multiagent systems
- function approximation
- planning problems
- model free
- state space
- autonomous agents
- learning algorithm
- complex environments
- decision problems
- markov decision process
- utility function
- optimal policy
- control policies
- decision makers
- dynamic programming
- neural network