Sandip Sen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sandip Sen has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
Anish Biswas
University of Tulsa
1 shared publication- Bikramjit Banerjee
Tulane University
1 shared publication - Edmund H. Durfee
Artificial Intelligence Laboratory The University of Michigan 1101 Beal Avenue Ann Arbor 48109-2110 Michigan
1 shared publication - Jing Peng
Tulane University
1 shared publication Parijat Prosun Kar
Mathematical and Computer Sciences Department , University of Tulsa , Tulsa, OK, 74104, USA
1 shared publicationPartha Sarathi Dutta
Mathematical and Computer Sciences Department , University of Tulsa , Tulsa, OK, 74104, USA
1 shared publication
Latest Publications
- 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.
- 1 December 2002
- Published by Taylor & Francis in Connection Science
- Vol. 14 (4) , 335-344
Effect of individual opinions on group interactions
We have evaluated the effectiveness of a probabilistic reciprocity scheme for promoting co-operation among self-interested agents. The probabilistic reciprocity mechanism is used to determine whether an agent should co-operate when approached for help by another agent. The situation becomes more complex when a group of agents seeks help from another group. The opinions of the members of the helping group about each of the asking group members can be combined to evaluate such a request for help. Exploitative agents would want to be part of groups that receive help from other groups, but will try to prevent its group from helping other groups. Such agents, revealing false opinion about the reputation of others, can cause unwarranted rejection of help requests from other groups. This leads to global performance degradation in terms of reduced inter-group co-operation and increased cost for the individual agents. We study the viability of reciprocative agents in randomly formed groups and when groups are formed by agents contracting other helpful agents. Group helping decisions are based on both average and worst combined ratings of group members. A key result from our study is that lying exploitative agents, who provide false opinions about other agents, become ineffective when focused group selection is enabled.
- 1 December 2002
- Published by Taylor & Francis in Connection Science
- Vol. 14 (4) , 335-344
Effect of individual opinions on group interactions
We have evaluated the effectiveness of a probabilistic reciprocity scheme for promoting co-operation among self-interested agents. The probabilistic reciprocity mechanism is used to determine whether an agent should co-operate when approached for help by another agent. The situation becomes more complex when a group of agents seeks help from another group. The opinions of the members of the helping group about each of the asking group members can be combined to evaluate such a request for help. Exploitative agents would want to be part of groups that receive help from other groups, but will try to prevent its group from helping other groups. Such agents, revealing false opinion about the reputation of others, can cause unwarranted rejection of help requests from other groups. This leads to global performance degradation in terms of reduced inter-group co-operation and increased cost for the individual agents. We study the viability of reciprocative agents in randomly formed groups and when groups are formed by agents contracting other helpful agents. Group helping decisions are based on both average and worst combined ratings of group members. A key result from our study is that lying exploitative agents, who provide false opinions about other agents, become ineffective when focused group selection is enabled.
- 31 December 1997
- Published by Elsevier in Trends in Cognitive Sciences
- Vol. 1 (9) , 334-340
Multiagent systems: Milestones and new horizons
- 31 December 1997
- Published by Elsevier in Trends in Cognitive Sciences
- Vol. 1 (9) , 334-340
Multiagent systems: Milestones and new horizons
- 1 August 1996
- Published by Springer Nature in Annals of Operations Research
- Vol. 65 (1) , 195-222
A contracting model for flexible distributed scheduling
- 1 August 1996
- Published by Springer Nature in Annals of Operations Research
- Vol. 65 (1) , 195-222
A contracting model for flexible distributed scheduling