ArrayBot: Reinforcement Learning for Generalizable Distributed Manipulation through Touch.
Zhengrong XueHan ZhangJingwen ChengZhengmao HeYuanchen JuChangyi LinGu ZhangHuazhe XuPublished in: ICRA (2024)
Keyphrases
- reinforcement learning
- multi agent
- distributed environment
- function approximation
- databases
- model free
- cooperative
- computer networks
- data sets
- distributed network
- distributed learning
- reinforcement learning algorithms
- communication cost
- fault tolerant
- distributed systems
- dynamic programming
- learning process
- peer to peer
- case study
- distributed data
- database
- temporal difference learning
- learning algorithm
- distributed architecture
- communication overhead
- metadata
- temporal difference
- optimal control
- hidden markov models
- state space
- optimal policy