Research map / Reinforcement learning / MDPs and planning
Stochastic Principal-Agent Problems: Computing and Learning Optimal History-Dependent Policies
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies a stochastic principal-agent model with far-sighted players and commitment, computing and learning optimal history-dependent policies for the principal and agent.
Problem
Optimal coordination and information elicitation in a stochastic principal-agent setting where the principal and agent each hold private state observations and interact over time.
Approach
Models a stochastic principal-agent interaction with commitment by the principal, where both players are far-sighted and communicate before independently selecting actions, and studies computing and learning optimal history-dependent policies.
Closest papers by meaning
- Online Reinforcement Learning in Stochastic Games (NeurIPS 2017 · similarity 0.87)
- Horizon-free Learning for Markov Decision Processes and Games: Stochastically Bounded Rewards and Improved Bounds (ICML 2023 · similarity 0.87)
- Learning Optimal Contracts: How to Exploit Small Action Spaces (ICLR 2024 · similarity 0.87)
- Learning in Online Principal-Agent Interactions: The Power of Menus (AAAI 2024 · similarity 0.86)
- Learning to Steer Markovian Agents under Model Uncertainty (ICLR 2025 · similarity 0.86)
- Incentivized Learning in Principal-Agent Bandit Games (ICML 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.