Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning.
Jinning LiChen TangMasayoshi TomizukaWei ZhanPublished in: IEEE Robotics Autom. Lett. (2022)
Keyphrases
- reinforcement learning
- function approximation
- real time
- artificial intelligence
- learning algorithm
- state space
- robot control
- information retrieval
- multi agent systems
- learning classifier systems
- markov decision processes
- dynamic environments
- dynamic programming
- learning process
- multi agent
- objective function
- search engine
- neural network