Journal of the ACM (JACM)
Incentive-compatible online auctions for digital goods
SODA '02 Proceedings of the thirteenth annual ACM-SIAM symposium on Discrete algorithms
Online learning in online auctions
SODA '03 Proceedings of the fourteenth annual ACM-SIAM symposium on Discrete algorithms
Gambling in a rigged casino: The adversarial multi-armed bandit problem
FOCS '95 Proceedings of the 36th Annual Symposium on Foundations of Computer Science
The Value of Knowing a Demand Curve: Bounds on Regret for Online Posted-Price Auctions
FOCS '03 Proceedings of the 44th Annual IEEE Symposium on Foundations of Computer Science
Negotiation-range mechanisms: exploring the limits of truthful efficient markets
EC '04 Proceedings of the 5th ACM conference on Electronic commerce
Mechanism design for online real-time scheduling
EC '04 Proceedings of the 5th ACM conference on Electronic commerce
Self-interested automated mechanism design and implications for optimal combinatorial auctions
EC '04 Proceedings of the 5th ACM conference on Electronic commerce
Sequential information elicitation in multi-agent systems
UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Searching for stable mechanisms: automated design for imperfect players
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
GROWRANGE: anytime VCG-based mechanisms
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Mechanism design for single-value domains
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 1
Sequential-simultaneous information elicitation in multi-agent systems
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Agent learning in the multi-agent contracting system [MACS]
Decision Support Systems
Learn while you earn: two approaches to learning auction parameters in take-it-or-leave-it auctions
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 3
Learning the demand curve in posted-price digital goods auctions
The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 1
Efficient bidding strategies for Cliff-Edge problems
Autonomous Agents and Multi-Agent Systems
Hi-index | 0.00 |
In a principal-agent problem, a principal seeks to motivate an agent to take a certain action beneficial to the principal, while spending as little as possible on the reward. This is complicated by the fact that the principal does not know the agent's utility function (or type). We study the online setting where at each round, the principal encounters a new agent, and the principal sets the rewards anew. At the end of each round, the principal only finds out the action that the agent took, but not his type. The principal must learn how to set the rewards optimally. We show that this setting generalizes the setting of selling a digital good online.We study and experimentally compare three main approaches to this problem. First, we show how to apply a standard bandit algorithm to this setting. Second, for the case where the distribution of agent types is fixed (but unknown to the principal), we introduce a new gradient ascent algorithm. Third, for the case where the distribution of agents' types is fixed, and the principal has a prior belief (distribution) over a limited class of type distributions, we study a Bayesian approach.