Bi-Manual Manipulation and Attachment via Sim-to-Real Reinforcement Learning.
Satoshi KataokaSeyed Kamyar Seyed GhasemipourC. Daniel FreemanIgor MordatchPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- multi agent
- error prone
- dynamic programming
- data sets
- model free
- information systems
- function approximation
- real life
- markov decision processes
- semi automatic
- multi agent reinforcement learning
- optimal policy
- business intelligence
- mobile robot
- learning process
- search space
- artificial neural networks
- learning algorithm
- neural network