Parallel Recombinative Reinforcement Learning (Extended Abstract).
Aristidis LikasKonstantinos BlekasAndreas StafylopatisPublished in: ECML (1995)
Keyphrases
- extended abstract
- reinforcement learning
- database
- learning algorithm
- state space
- parallel processing
- function approximation
- multi agent
- multi agent reinforcement learning
- reinforcement learning algorithms
- robotic control
- parallel hardware
- parallel execution
- parallel architectures
- temporal difference
- parallel implementation
- shared memory
- optimal policy
- least squares
- hidden markov models
- learning process
- real time