RL-RRT: Kinodynamic Motion Planning via Learning Reachability Estimators from RL Policies.
Hao-Tien Lewis ChiangJasmine HsuMarek FiserLydia TapiaAleksandra FaustPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- motion planning
- learning process
- learning algorithm
- autonomous learning
- mobile robot
- optimal policy
- function approximation
- path planning
- learning agents
- state space
- action selection
- model free
- policy search
- trajectory planning
- viewpoint
- partially observable
- markov decision processes
- multiagent reinforcement learning
- robotic tasks