Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity.
Jinghao XinJinwoo KimZhi LiNing LiPublished in: CoRR (2023)
Keyphrases
- path planner
- real world
- reinforcement learning
- robot path planning
- robot soccer
- cellular automata
- path planning
- mobile robot
- action selection
- real robot
- international space station
- machine learning
- data mining
- markov decision processes
- dynamic environments
- spatial reasoning
- optimal policy
- state space
- collision free
- decision making