Trajectory Planning with Deep Reinforcement Learning in High-Level Action Spaces.
Kyle R. WilliamsRachel SchlossmanDaniel WhittenJoe IngramSrideep MusuvathyAnirudh PatelJames PaganKyle A. WilliamsSam GreenAnirban MazumdarJulie ParishPublished in: CoRR (2021)
Keyphrases
- action space
- trajectory planning
- reinforcement learning
- state space
- state and action spaces
- markov decision processes
- continuous state
- motion planning
- robot manipulators
- real valued
- obstacle avoidance
- path planning
- dynamic environments
- skill learning
- continuous state spaces
- action selection
- markov decision process
- stochastic processes
- mobile robot
- markov decision problems
- optimal policy
- reinforcement learning algorithms
- model free
- single agent
- function approximation
- function approximators
- state action
- dynamic programming
- computer vision
- decision making
- partially observable
- learning algorithm
- humanoid robot
- optimal solution
- multi agent