Basic Research on Speed-Up of Reinforcement Learning Using Parallel Processing for Combination Value Function.
Tsuguhisa ToumaYuuki NakamaKoji YamadaSatoshi EndoPublished in: Complex Adaptive Systems (2011)
Keyphrases
- parallel processing
- reinforcement learning
- processing speed
- computational power
- distributed processing
- parallel architectures
- machine learning
- function approximation
- parallel computation
- ibm sp
- electronic circuits
- pc cluster
- reinforcement learning algorithms
- markov decision processes
- general purpose
- state space
- model free
- parallel programming
- parallel computers
- parallel architecture
- detection algorithm
- computer systems