by Vincent Conitzer, Nikesh Garera
In: Proceedings of the 23rd International Conference on Machine Learning (ICML-06
http://www.cs.cmu.edu/~conitzer/principalICML06.pdf
Add To MetaCart
Abstract:
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. 1.
Citations
|
534
|
J.R.: Microeconomic Theory
– Mas-Colell, Whinston
- 1995
|
|
228
|
How to use expert advice
– Cesa-Bianchi, Freund, et al.
- 1997
|
|
103
|
Gambling in a rigged casino: The adversarial multi-armed bandit problem
– Auer, Cesa-Bianchi, et al.
- 1995
|
|
43
|
Incentive-compatible online auctions for digital goods
– Bar-Yossef, Hildrum, et al.
- 2002
|
|
37
|
Online learning in online auctions
– Blum, Kumar, et al.
- 2003
|
|
19
|
The value of knowing a demand curve: Bounds on regret for online posted-price auctions
– Kleinberg, Leighton
- 2003
|
|
18
|
Mechanism design for single-value domains
– Babaioff, Lavi, et al.
- 2005
|
|
17
|
How to combine expert (or novice) advice when actions impact the environment
– Farias, Megiddo
|
|
14
|
Mechanism design for online real-time scheduling
– Porter
- 2004
|
|
13
|
Self-interested automated mechanism design and implications for optimal combinatorial auctions
– Conitzer, Sandholm
- 2004
|
|
6
|
GROWRANGE: Anytime VCG-based mechanisms
– Parkes, Schoenebeck
- 2004
|
|
3
|
Sequential information elicitation in multi-agent systems
– Smorodinsky, Tennenholtz
- 2004
|
|
3
|
Negotiation-range mechanisms: Exploring the limits of truthful efficient markets
– Bartal, Gonen, et al.
- 2004
|
|
3
|
Searching for stable mechanisms: Automated design for imperfect players
– Blumberg, Shelat
- 2004
|
