AIConfPaper
← Search

Minqi Jiang

22 accepted papers

2025

AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench

Edan Toledo, Karen Hambardzumyan, Martin Josifoski, RISHI HAZRA, Nicolas Baldwin, Alexis Audran-Reiss +19
NeurIPS 2025spotlight

AI research agents are demonstrating great potential to accelerate scientific progress by automating the design, implementation, and training of machine learning models. We focus on methods for improving agents' performance on MLE-bench, a challenging benchmark where agents compete in Kaggle competi…

Cited by 0Source ↗code ↗Scholar ↗
2025

Combining Code Generating Large Language Models and Self-Play to Iteratively Refine Strategies in Games

Yoram Bachrach, Edan Toledo, Karen Hambardzumyan, Despoina Magka, Martin Josifoski, Minqi Jiang +8
IJCAI 2025

We propose a self-play approach to generating strategies for playing in multi-player games, where strategies are represented as computer code. We use large language models (LLMs) to generate pieces of code to play in the game, which we refer to as generated bots. We engage the LLM generated bots in

Cited by 0Source ↗PDF ↗Scholar ↗
2025

The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements

Bingchen Zhao, Despoina Magka, Minqi Jiang, Xian Li, Roberta Raileanu, Tatiana Shavrina +17
NeurIPS 2025poster

Rapidly improving large language models (LLMs) have the potential to assist in scientific progress. One critical skill in this endeavor is the ability to faithfully reproduce existing work. To evaluate the capability of AI agents to reproduce complex code in an active research area, we introduce the…

Cited by 0Source ↗code ↗Scholar ↗
2024

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX

Alexander Rutherford, Benjamin Ellis, Matteo Gallici, Jonathan Cook, Andrei Lupu, Garðar Ingvarsson +15
NeurIPS 2024poster

Benchmarks are crucial in the development of machine learning algorithms, significantly influencing reinforcement learning (RL) research through the available environments. Traditionally, RL environments run on the CPU, which limits their scalability with the computational resources typically availa…

Cited by 20Source ↗PDF ↗code ↗Scholar ↗
2024

Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts

Mikayel Samvelyan, Sharath Chandra Raparthy, Andrei Lupu, Eric Hambro, Aram H. Markosyan, Manish Bhatt +6
NeurIPS 2024poster

As large language models (LLMs) become increasingly prevalent across many real-world applications, understanding and enhancing their robustness to adversarial attacks is of paramount importance. Existing methods for identifying adversarial prompts tend to focus on specific domains, lack diversity, o…

Cited by 71Source ↗PDF ↗Scholar ↗
2024

Refining Minimax Regret for Unsupervised Environment Design

Michael Beukman, Samuel Coward, Michael Matthews, Mattie Fellows, Minqi Jiang, Michael D Dennis +1
ICML 2024poster

In unsupervised environment design, reinforcement learning agents are trained on environment configurations (levels) generated by an adversary that maximises some objective. Regret is a commonly used objective that theoretically results in a minimax regret (MMR) policy with desirable robustness guar…

Cited by 12Source ↗PDF ↗code ↗Scholar ↗
2024

The Generalization Gap in Offline Reinforcement Learning

Ishita Mediratta, Qingfei You, Minqi Jiang, Roberta Raileanu
ICLR 2024poster

Despite recent progress in offline learning, these methods are still trained and tested on the same environment. In this paper, we compare the generalization abilities of widely used online and offline learning methods such as online reinforcement learning (RL), offline RL, sequence modeling, and be…

Cited by 17Source ↗PDF ↗code ↗Scholar ↗
2023

A Study of Global and Episodic Bonuses for Exploration in Contextual MDPs

Mikael Henaff, Minqi Jiang, Roberta Raileanu
ICML 2023oral

Exploration in environments which differ across episodes has received increasing attention in recent years. Current methods use some combination of global novelty bonuses, computed using the agent's entire training experience, and episodic novelty bonuses, computed using only experience from the cur…

Cited by 19Source ↗PDF ↗code ↗Scholar ↗
2023

ADGym: Design Choices for Deep Anomaly Detection

Minqi Jiang, Chaochuan Hou, Ao Zheng, Songqiao Han, Hailiang Huang, Qingsong Wen +2
NeurIPS 2023poster

Deep learning (DL) techniques have recently found success in anomaly detection (AD) across various fields such as finance, medical services, and cloud computing. However, most of the current research tends to view deep AD algorithms as a whole, without dissecting the contributions of individual desi…

Cited by 16Source ↗PDF ↗code ↗Scholar ↗
2023

Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design

Matthew Thomas Jackson, Minqi Jiang, Jack Parker-Holder, Risto Vuorio, Chris Lu, Gregory Farquhar +2
NeurIPS 2023poster

The past decade has seen vast progress in deep reinforcement learning (RL) on the back of algorithms manually designed by human researchers. Recently, it has been shown that it is possible to meta-learn update rules, with the hope of discovering algorithms that can perform well on a wide range of RL…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2023

MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning

Mikayel Samvelyan, Akbir Khan, Michael D Dennis, Minqi Jiang, Jack Parker-Holder, Jakob Nicolaus Foerster +2
ICLR 2023poster

Open-ended learning methods that automatically generate a curriculum of increasingly challenging tasks serve as a promising avenue toward generally capable reinforcement learning agents. Existing methods adapt curricula independently over either environment parameters (in single-agent settings) or c…

Cited by 41Source ↗PDF ↗Scholar ↗
2022

Evolving Curricula with Regret-Based Environment Design

Jack Parker-Holder, Minqi Jiang, Michael Dennis, Mikayel Samvelyan, Jakob Foerster, Edward Grefenstette +1
ICML 2022spotlight

Training generally-capable agents with reinforcement learning (RL) remains a significant challenge. A promising avenue for improving the robustness of RL agents is through the use of curricula. One such class of methods frames environment design as a game between a student and a teacher, using regre…

Cited by 148Source ↗PDF ↗code ↗Scholar ↗
2022

Exploration via Elliptical Episodic Bonuses

Mikael Henaff, Roberta Raileanu, Minqi Jiang, Tim Rocktäschel
NeurIPS 2022accept

In recent years, a number of reinforcement learning (RL) methods have been pro- posed to explore complex environments which differ across episodes. In this work, we show that the effectiveness of these methods critically relies on a count-based episodic term in their exploration bonus. As a result,…

Cited by 48Source ↗PDF ↗code ↗Scholar ↗
2022

GriddlyJS: A Web IDE for Reinforcement Learning

Christopher Bamford, Minqi Jiang, Mikayel Samvelyan, Tim Rocktäschel
NeurIPS 2022accept

Progress in reinforcement learning (RL) research is often driven by the design of new, challenging environments---a costly undertaking requiring skills orthogonal to that of a typical machine learning researcher. The complexity of environment development has only increased with the rise of procedura…

Cited by 7Source ↗PDF ↗Scholar ↗
2022

Grounding Aleatoric Uncertainty for Unsupervised Environment Design

Minqi Jiang, Michael D Dennis, Jack Parker-Holder, Andrei Lupu, Heinrich Kuttler, Edward Grefenstette +2
NeurIPS 2022accept

Adaptive curricula in reinforcement learning (RL) have proven effective for producing policies robust to discrepancies between the train and test environment. Recently, the Unsupervised Environment Design (UED) framework generalized RL curricula to generating sequences of entire environments, leadin…

Cited by 19Source ↗PDF ↗Scholar ↗
2022

Improving Intrinsic Exploration with Language Abstractions

Jesse Mu, Victor Zhong, Roberta Raileanu, Minqi Jiang, Noah Goodman, Tim Rocktäschel +1
NeurIPS 2022accept

Reinforcement learning (RL) agents are particularly hard to train when rewards are sparse. One common solution is to use intrinsic rewards to encourage agents to explore their environment. However, recent intrinsic exploration methods often use state-based novelty measures which reward low-level exp…

Cited by 71Source ↗PDF ↗Scholar ↗
2021

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

Mikayel Samvelyan, Robert Kirk, Vitaly Kurin, Jack Parker-Holder, Minqi Jiang, Eric Hambro +4
NeurIPS 2021poster

Progress in deep reinforcement learning (RL) is heavily driven by the availability of challenging benchmarks used for training agents. However, benchmarks that are widely adopted by the community are not explicitly designed for evaluating specific capabilities of RL methods. While there exist enviro…

Cited by 108Source ↗code ↗Scholar ↗
2021

Replay-Guided Adversarial Environment Design

Minqi Jiang, Michael D Dennis, Jack Parker-Holder, Jakob Nicolaus Foerster, Edward Grefenstette, Tim Rocktäschel
NeurIPS 2021poster

Deep reinforcement learning (RL) agents may successfully generalize to new settings if trained on an appropriately diverse set of environment and task configurations. Unsupervised Environment Design (UED) is a promising self-supervised RL paradigm, wherein the free parameters of an underspecified en…

Cited by 119Source ↗PDF ↗Scholar ↗