Market-Based Dynamic Task Allocation Using Heuristically Accelerated Reinforcement Learning.
José Angelo GurzoniFlavio TonidandelReinaldo A. C. BianchiPublished in: EPIA (2011)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- temporal difference
- model free
- stock market
- learning algorithm
- reinforcement learning algorithms
- stock price
- action selection
- multi agent
- financial markets
- financial data
- market share
- learning process
- machine learning
- control policy
- double auction