Learning approximately optimal contracts
From MaRDI portal
Abstract: In principal-agent models, a principal offers a contract to an agent to perform a certain task. The agent exerts a level of effort that maximizes her utility. The principal is oblivious to the agent's chosen level of effort, and conditions her wage only on possible outcomes. In this work, we consider a model in which the principal is unaware of the agent's utility and action space: she sequentially offers contracts to identical agents, and observes the resulting outcomes. We present an algorithm for learning the optimal contract under mild assumptions. We bound the number of samples needed for the principal to obtain a contract that is within of her optimal net profit for every . Our results are robust even when considering risk-averse agents. Furthermore, we show that when there are only two possible outcomes or the agent is risk-neutral, the algorithm's outcome approximates the optimal contract described in the classical theory.
Recommendations
- Learning approximately optimal contracts
- Optimal contracts
- Optimal contracts for agents with adverse selection
- A variational approach to contracting under imperfect observations
- Optimal contracts in continuous-time models
- Optimal contracts with contingent allocation
- Implementation of optimal contracts under adverse selection
- Computing optimal contracts in combinatorial agencies
- Minimum-regret contracts for principal-expert problems
- Optimal contracts with a risk-taking agent
Cites work
- 2021 IEEE 62nd Annual Symposium on Foundations of Computer Science (FOCS)
- A Continuous-Time Version of the Principal–Agent Problem
- Action elimination and stopping conditions for the multi-armed bandit and reinforcement learning problems
- Adaptive contract design for crowdsourcing markets: bandit algorithms for repeated principal-agent problems
- An Analysis of the Principal-Agent Problem
- Bandits and Experts in Metric Spaces
- Bayesian agency: linear versus tractable contracts
- Combinatorial agency
- Dynamic contracts with moral hazard and adverse selection
- Improved Rates for the Stochastic Continuum-Armed Bandit Problem
- Lipschitz bandits without the Lipschitz constant
- Microeconomic theory
- Mixed strategies in combinatorial agency
- Risk Aversion in the Small and in the Large
- The complexity of contracts
- The Continuum-Armed Bandit Problem
Cited in
(18)- Dynamic principal agent model based on CMDP
- Robust pooling for contracting models with asymmetric information
- Robustness and approximation for the linear contract design
- Learning from failures: optimal contracts for experimentation and production
- Minimum-regret contracts for principal-expert problems
- Adaptive contract design for crowdsourcing markets: bandit algorithms for repeated principal-agent problems
- Sellers with misspecified models
- Computational principal-agent problems
- Optimal contract design for effort-averse sensors
- On selecting the right agent
- The complexity of contracts
- Learning by doing vs. learning from others in a principal-agent model
- Data-driven contract design
- Learning strategies for outsourcing problems with asymmetric information and uncertain execution
- Approximating continuous multi-agent contracts with Lyapunov function methods
- Learning optimal contracts with small action spaces
- Algorithmic contract theory: a survey
- Computing optimal contracts in combinatorial agencies
This page was built for publication: Learning approximately optimal contracts
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6109528)
