10 papers
Learning to Drive in New Cities Without Human Demonstrations
Zilin Wang, Saeed Rahmani, Daphne Cornelisse +4
While autonomous vehicles have achieved reliable performance within specific operating regions, their deployment to new cities remains costly and slow. A key bottleneck is the need…
How Should We Meta-Learn Reinforcement Learning Algorithms?
Alexander David Goldie, Zilin Wang, Jaron Cohen +2
The process of meta-learning algorithms from data, instead of relying on manual design, is growing in popularity as a paradigm for improving the performance of machine learning sys…
AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
Edan Toledo, Karen Hambardzumyan, Martin Josifoski +22
AI research agents are demonstrating great potential to accelerate scientific progress by automating the design, implementation, and training of machine learning models. We focus o…
The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements
Bingchen Zhao, Despoina Magka, Minqi Jiang +20
Rapid advancements in large language models (LLMs) have the potential to assist in scientific progress. A critical capability toward this endeavor is the ability to reproduce exist…
Ad-Hoc Human-AI Coordination Challenge
Tin Dizdarević, Ravi Hammond, Tobias Gessler +7
Achieving seamless coordination between AI agents and humans is crucial for real-world applications, yet it remains a significant open challenge. Hanabi is a cooperative card game…
The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind
Andrei Lupu, Timon Willi, Jakob Foerster
As Large Language Models (LLMs) gain agentic abilities, they will have to navigate complex multi-agent scenarios, interacting with human users and other agents in cooperative and c…
OvercookedV2: Rethinking Overcooked for Zero-Shot Coordination
Tobias Gessler, Tin Dizdarevic, Ani Calinescu +3
AI agents hold the potential to transform everyday life by helping humans achieve their goals. To do this successfully, agents need to be able to coordinate with novel partners wit…
Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps
Benjamin Ellis, Matthew T. Jackson, Andrei Lupu +4
In reinforcement learning (RL), it is common to apply techniques used broadly in machine learning such as neural network function approximators and momentum-based optimizers. Howev…
Beyond the Boundaries of Proximal Policy Optimization
Charlie B. Tan, Edan Toledo, Benjamin Ellis +2
Proximal policy optimization (PPO) is a widely-used algorithm for on-policy reinforcement learning. This work offers an alternative perspective of PPO, in which it is decomposed in…
CURATe: Benchmarking Personalised Alignment of Conversational AI Assistants
Lize Alberts, Benjamin Ellis, Andrei Lupu +1
We introduce a multi-turn benchmark for evaluating personalised alignment in LLM-based AI assistants, focusing on their ability to handle user-provided safety-critical contexts. Ou…