Search Results for author:
Found 9 papers, 6 papers with code
Solving Dynamic Principal-Agent Problems with a Rationally Inattentive Principal
In a sequential setting with multiple Agents, RIRL shows opposing consequences of the Principal's inattention to different information channels: 1) inattention to Agents' outputs closes wage gaps based on ability differences; and 2) inattention to Agents' efforts induces a social dilemma dynamic in which Agents work harder, but essentially for free.
Deep Reinforcement Learning
Multi-agent Reinforcement Learning
Analyzing Micro-Founded General Equilibrium Models with Many Agents using Deep Reinforcement Learning
We validate the learned solutions are $\epsilon$-meta-equilibria through best-response analyses, show that they align with economic intuitions, and show our approach can learn a spectrum of qualitatively distinct $\epsilon$-meta-equilibria in open RBC models.
Deep Reinforcement Learning
Multi-agent Reinforcement Learning
+2
Building a Foundation for Data-Driven, Interpretable, and Robust Policy Design using the AI Economist
Here we show that the AI Economist framework enables effective, flexible, and interpretable policy design using two-level reinforcement learning (RL) and data-driven simulations.
The AI Economist: Optimal Economic Policy Design via Two-level Deep Reinforcement Learning
Here we show that machine-learning-based economic simulation is a powerful policy and mechanism design framework to overcome these limitations.
The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies
In experiments conducted on MTurk, an AI tax policy provides an equality-productivity trade-off that is similar to that provided by the Saez framework along with higher inverse-income weighted social welfare.
Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills
We perform an extensive evaluation of skill discovery methods on controlled environments and show that EDL offers significant advantages, such as overcoming the coverage problem, reducing the dependence of learned skills on the initial state, and allowing the user to define a prior over which behaviors should be learned.
Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards
For instance, in tasks where the agent must achieve some goal state, simple distance-to-goal reward shaping often fails, as it renders learning vulnerable to local optima.
Competitive Experience Replay
We propose a novel method called competitive experience replay, which efficiently supplements a sparse reward by placing learning in the context of an exploration competition between a pair of agents.
Interpretable Counting for Visual Question Answering
Questions that require counting a variety of objects in images remain a major challenge in visual question answering (VQA).
