A
Alexander Trott
Researcher at Salesforce.com
Publications - 30
Citations - 473
Alexander Trott is an academic researcher from Salesforce.com. The author has contributed to research in topics: Reinforcement learning & Computer science. The author has an hindex of 12, co-authored 21 publications receiving 286 citations. Previous affiliations of Alexander Trott include Brandeis University & Harvard University.
Papers
More filters
Posted Content
The AI Economist: Improving Equality and Productivity with AI-Driven Tax Policies
Stephan Zheng,Alexander Trott,Sunil Srinivasa,Nikhil Naik,Melvin Gruesbeck,David C. Parkes,Richard Socher +6 more
TL;DR: This work proposes a two-level deep reinforcement learning approach to learn dynamic tax policies, based on economic simulations in which both agents and a government learn and adapt, and shows that AI-driven tax policies perform strongly in the face of emergent tax-gaming strategies learned by AI agents.
Proceedings Article
Explore, Discover and Learn: Unsupervised Discovery of State-Covering Skills
TL;DR: This work performs an extensive evaluation of skill discovery methods on controlled environments and shows 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.
Proceedings Article
Interpretable Counting for Visual Question Answering
TL;DR: In this article, the authors treat counting as a sequential decision process and force their model to make discrete choices of what to count, and learn interactions between objects that influence subsequent selections.
Posted Content
Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards
TL;DR: This work introduces a simple and effective model-free method to learn from shaped distance-to-goal rewards on tasks where success depends on reaching a goal state and introduces an auxiliary distance-based reward based on pairs of rollouts to encourage diverse exploration.
Journal ArticleDOI
Input-Gain Control Produces Feature-Specific Surround Suppression
Alexander Trott,Richard T. Born +1 more
TL;DR: The stability of implanted multielectrode arrays is exploited to record from neurons in V1 of alert monkeys with multiple stimulus sets that more exhaustively probed center-surround interactions, providing key physiological support for theoretical models that propose feature-specific, input-gain control as the mechanism underlying surround suppression.