A Social Reinforcement Learning Agent (2001)

by Charles L. Isbell, Christian R. Shelton, Michael Kearns, Satinder Singh, and Peter Stone


Abstract: We report on our reinforcement learning work on Cobot, a software agent that resides in a the well-known online chat community LambdaMOO. Our initial work on Cobot (Isbell et al., 2000) provided him with the ability to collect social statistics and report them to users in a reactive manner. Here we describe our application of reinforcement learning to allow Cobot to proactively take actions in this complex social environment, and adapt this behavior from multiple sources of human reward. After 5 months of training, Cobot has received 3171 reward and punishment events from 254 different LambdaMOO users, and has learned nontrivial preferences for a number of users. Cobot modifies his behavior based on his current state in an attempt to maximize reward. Here we describe LambdaMOO and the state and action spaces of Cobot, and report the statistical results of the learning experiment.

Download Information

Charles L. Isbell, Christian R. Shelton, Michael Kearns, Satinder Singh, and Peter Stone (2001). "A Social Reinforcement Learning Agent." Fifth International Conference on Autonomous Agents (pp. 377-384). best paper award. pdf   ps ps.gz    

Bibtex citation

@inproceedings{IsbSheKeaSinSto01,
   author = "Charles L. Isbell and Christian R. Shelton and Michael Kearns and Satinder Singh and Peter Stone",
   title = "A Social Reinforcement Learning Agent",
   booktitle = "Fifth International Conference on Autonomous Agents",
   booktitleabbr = "Agents",
   pages = "377--384",
   year = 2001,
}