21 citations · 45 across the 4 of their papers we have counts for
7 papers
Learning to Play General-Sum Games Against Multiple Boundedly Rational Agents
Eric Zhao, Alexander R. Trott, Caiming Xiong +1
We study the problem of training a principal in a multi-agent general-sum game using reinforcement learning (RL). Learning a robust principal policy requires anticipating the worst…
Robustness Gym: Unifying the NLP Evaluation Landscape
Karan Goel, Nazneen Rajani, Jesse Vig +6
Despite impressive performance on standard benchmarks, deep neural networks are often brittle when deployed in real-world systems. Consequently, recent research has focused on test…
ESPRIT: Explaining Solutions to Physical Reasoning Tasks
Nazneen Fatema Rajani, Rui Zhang, Yi Chern Tan +7
Neural networks lack the ability to reason about qualitative physics and so cannot generalize to scenarios and tasks unseen during training. We propose ESPRIT, a framework for comm…
Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards
Alexander Trott, Stephan Zheng, Caiming Xiong +1
While using shaped rewards can be beneficial when solving sparse reward tasks, their successful application often requires careful engineering and is problem specific. For instance…
Sketch-Fill-A-R: A Persona-Grounded Chit-Chat Generation Framework
Michael Shum, Stephan Zheng, Wojciech Kryściński +2
Human-like chit-chat conversation requires agents to generate responses that are fluent, engaging and consistent. We propose Sketch-Fill-A-R, a framework that uses a persona-memory…
Learning World Graphs to Accelerate Hierarchical Reinforcement Learning
Wenling Shang, Alex Trott, Stephan Zheng +2
In many real-world scenarios, an autonomous agent often encounters various tasks within a single complex environment. We propose to build a graph abstraction over the environment s…
On the Generalization Gap in Reparameterizable Reinforcement Learning
Huan Wang, Stephan Zheng, Caiming Xiong +1
Understanding generalization in reinforcement learning (RL) is a significant challenge, as many common assumptions of traditional supervised learning theory do not apply. We focus…