Jing Peng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jing Peng has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Bikramjit Banerjee
Tulane University
2 shared publications - Douglas R. Heisterkamp
Oklahoma State University
1 shared publication - Sandip Sen
University of Tulsa
1 shared publication
Latest Publications
- 8 June 2007
- Published by Springer Nature in Autonomous Agents and Multi-Agent Systems
- Vol. 15 (3) , 281-312
Generalized multiagent learning with performance bound
- 8 June 2007
- Published by Springer Nature in Autonomous Agents and Multi-Agent Systems
- Vol. 15 (3) , 281-312
Generalized multiagent learning with performance bound
- 1 June 2005
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 26 (2) , 175-189
Kernel Vector Approximation Files for Relevance Feedback Retrieval in Large Image Databases
- 1 June 2005
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 26 (2) , 175-189
Kernel Vector Approximation Files for Relevance Feedback Retrieval in Large Image Databases
- 1 October 2004
- Published by Taylor & Francis in Journal of Experimental & Theoretical Artificial Intelligence
- Vol. 16 (4) , 245-260
On-policy concurrent reinforcement learning
When an agent learns in a multi-agent environment, the payoff it receives is dependent on the behaviour of the other agents. If the other agents are also learning, its reward distribution becomes non-stationary. This makes learning in multi-agent systems more difficult than single-agent learning. Prior attempts at value-function based learning in such domains have used off-policy Q-learning that do not scale well as the cornerstone, with restricted success. This paper studies on-policy modifications of such algorithms, with the promise of scalability and efficiency. In particular, it is proven that these hybrid techniques are guaranteed to converge to their desired fixed points under some restrictions. It is also shown, experimentally, that the new techniques can learn (from self-play) better policies than the previous algorithms (also in self-play) during some phases of the exploration.
- 1 October 2004
- Published by Taylor & Francis in Journal of Experimental & Theoretical Artificial Intelligence
- Vol. 16 (4) , 245-260
On-policy concurrent reinforcement learning
When an agent learns in a multi-agent environment, the payoff it receives is dependent on the behaviour of the other agents. If the other agents are also learning, its reward distribution becomes non-stationary. This makes learning in multi-agent systems more difficult than single-agent learning. Prior attempts at value-function based learning in such domains have used off-policy Q-learning that do not scale well as the cornerstone, with restricted success. This paper studies on-policy modifications of such algorithms, with the promise of scalability and efficiency. In particular, it is proven that these hybrid techniques are guaranteed to converge to their desired fixed points under some restrictions. It is also shown, experimentally, that the new techniques can learn (from self-play) better policies than the previous algorithms (also in self-play) during some phases of the exploration.