Action-Quantized Offline Reinforcement Learning for Robotic Skill Learning.
Jianlan LuoPerry DongJeffrey WuAviral KumarXinyang GengSergey LevinePublished in: CoRL (2023)
Keyphrases
- skill learning
- action space
- reinforcement learning
- state space
- action selection
- real time
- markov decision processes
- real valued
- robot arm
- real robot
- stochastic processes
- machine learning
- robotic systems
- mobile robot
- dynamic programming
- markov decision process
- optimal policy
- multi agent systems
- multi agent
- decision making
- learning algorithm