AIConfPaper
← Search

Stephan Zheng

11 accepted papers

2025

AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N

Tianyu Zhang, Andrew Robert Williams, Phillip Wozny, Kai-Hendrik Cohrs, Koen Ponse, Marco Jiralerspong +9
ICML 2025poster

Global cooperation on climate change mitigation is essential to limit temperature increases while supporting long-term, equitable economic growth and sustainable development. Achieving such cooperation among diverse regions, each with different incentives, in a dynamic environment shaped by complex…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗
2025

EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths

Zhening Li, Armando Solar-Lezama, Yisong Yue, Stephan Zheng
NeurIPS 2025poster

We introduce a new approach to *agent programming*, the development of LLM-based agents. Current approaches to agent programming often entangle two aspects of agent design: the core workflow logic and the inference-time strategy (e.g., tree search). We introduce *probabilistic angelic nondeterminism…

Cited by 0Source ↗Scholar ↗
2024

Position: Social Environment Design Should be Further Developed for AI-based Policy-Making

Edwin Zhang, Sadie Zhao, Tonghan Wang, Safwan Hossain, Henry Gasztowtt, Stephan Zheng +3
ICML 2024poster

Artificial Intelligence (AI) holds promise as a technology that can be used to improve government and economic policy-making. This paper proposes a new research agenda towards this end by introducing **Social Environment Design**, a general framework for the use of AI in automated policy-making that…

Cited by 5Source ↗PDF ↗Scholar ↗
2023

Learning to Play General-Sum Games against Multiple Boundedly Rational Agents

Eric Zhao, Alexander R. Trott, Caiming Xiong, Stephan Zheng
AAAI 2023technical

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 possible strategic responses of other agents, which is generally NP-hard. However, we show that no-regret dynamics can…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2020

Multiresolution Tensor Learning for Efficient and Interpretable Spatial Analysis

Jung Yeon Park, Kenneth Carr, Stephan Zheng, Yisong Yue, Rose Yu
ICML 2020poster

Efficient and interpretable spatial analysis is crucial in many fields such as geology, sports, and climate science. Tensor latent factor models can describe higher-order correlations for spatial data. However, they are computationally expensive to train and are sensitive to initialization, leading…

Cited by 19Source ↗PDF ↗code ↗Scholar ↗
2019

Generating Multi-Agent Trajectories using Programmatic Weak Supervision

Eric Zhan, Stephan Zheng, Yisong Yue, Long Sha, Patrick Lucey
ICLR 2019poster

We study the problem of training sequential generative models for capturing coordinated multi-agent trajectory behavior, such as offensive basketball gameplay. When modeling such settings, it is often beneficial to design hierarchical models that can capture long-term coordination using intermedia…

Cited by 101Source ↗PDF ↗Scholar ↗
2019

Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards

Alexander Trott, Stephan Zheng, Caiming Xiong, Richard Socher
NeurIPS 2019poster

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, in tasks where the agent must achieve some goal state, simple distance-to-goal reward shaping often fails, as it rend…

Cited by 147Source ↗PDF ↗code ↗Scholar ↗
2019

NAOMI: Non-Autoregressive Multiresolution Sequence Imputation

Yukai Liu, Rose Yu, Stephan Zheng, Eric Zhan, Yisong Yue
NeurIPS 2019poster

Missing value imputation is a fundamental problem in spatiotemporal modeling, from motion tracking to the dynamics of physical systems. Deep autoregressive models suffer from error propagation which becomes catastrophic for imputing long-range sequences. In this paper, we take a non-autoregressive a…

Cited by 197Source ↗PDF ↗code ↗Scholar ↗
2019

On the Generalization Gap in Reparameterizable Reinforcement Learning

Huan Wang, Stephan Zheng, Caiming Xiong, Richard Socher
ICML 2019oral

Understanding generalization in reinforcement learning (RL) is a significant challenge, as many common assumptions of traditional supervised learning theory do not apply. We focus on the special class of reparameterizable RL problems, where the trajectory distribution can be decomposed using the rep…

Cited by 48Source ↗PDF ↗Scholar ↗
2016

Improving the Robustness of Deep Neural Networks via Stability Training

Stephan Zheng, Yang Song, Thomas Leung, Ian Goodfellow
CVPR 2016poster

In this paper we address the issue of output instability of deep neural networks: small perturbations in the visual input can significantly distort the feature embeddings and output of a neural network. Such instability affects many deep architectures with state-of-the-art performance on a wide rang…

Cited by 823PDF ↗Scholar ↗