Abstract | ||
---|---|---|
This paper thoroughly analyzes the transfer and construction of the state-action space of the agent decision-making process, discusses the optimal strategy of agent's action selection based on Markov decision-making process, designs a neural networks model for the agent reinforcement learning, and designs the agent reinforcement learning based on neural networks. By the simulation experiment of agent's bid price in Multi-Agent Electronic Commerce System, validated the Agent Reinforcement Learning Algorithm Based on Neural Networks has very good performance and the action impending ability. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1007/978-3-540-74769-7_14 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
null | Markov chain,Artificial intelligence,Engineering,Reinforcement learning algorithm,Artificial neural network,Error-driven learning,Action selection,Machine learning,Reinforcement learning,Learning classifier system,Bid price | Conference |
Volume | Issue | ISSN |
4688 | null | 0302-9743 |
Citations | PageRank | References |
0 | 0.34 | 3 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lianggui Tang | 1 | 1 | 2.04 |
Bo An | 2 | 892 | 106.05 |
Daijie Cheng | 3 | 9 | 3.22 |