Metaoptimization on a Distributed System for Deep Reinforcement Learning.
Greg HeinrichIuri FrosioPublished in: MLHPC@SC (2019)
Keyphrases
- distributed systems
- reinforcement learning
- fault tolerant
- function approximation
- data replication
- distributed computing
- message passing
- load balancing
- state space
- distributed environment
- reinforcement learning algorithms
- model free
- distributed database systems
- geographically distributed
- fault tolerance
- operating system
- optimal policy
- markov decision processes
- loosely coupled
- learning algorithm
- software architecture
- mobile agents
- multi agent
- security policies
- machine learning
- concurrent systems
- intelligent agents
- peer to peer
- agent technology
- software development
- mobile computing
- learning process
- temporal difference
- case study
- artificial intelligence
- learning agents