Advances of machine learning in materials science: Ideas and techniques

SS Chong, YS Ng, HQ Wang, JC Zheng - Frontiers of Physics, 2024‏ - Springer
In this big data era, the use of large dataset in conjunction with machine learning (ML) has
been increasingly popular in both industry and academia. In recent times, the field of …

Minigrid & miniworld: Modular & customizable reinforcement learning environments for goal-oriented tasks

M Chevalier-Boisvert, B Dai… - Advances in …, 2023‏ - proceedings.neurips.cc
We present the Minigrid and Miniworld libraries which provide a suite of goal-oriented 2D
and 3D environments. The libraries were explicitly created with a minimalistic design …

Promptbreeder: Self-referential self-improvement via prompt evolution

C Fernando, D Banarse, H Michalewski… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Popular prompt strategies like Chain-of-Thought Prompting can dramatically improve the
reasoning abilities of Large Language Models (LLMs) in various domains. However, such …

Rainbow teaming: Open-ended generation of diverse adversarial prompts

M Samvelyan, SC Raparthy, A Lupu… - Advances in …, 2025‏ - proceedings.neurips.cc
As large language models (LLMs) become increasingly prevalent across many real-world
applications, understanding and enhancing their robustness to adversarial attacks is of …

Human-timescale adaptation in an open-ended task space

AA Team, J Bauer, K Baumli, S Baveja… - arxiv preprint arxiv …, 2023‏ - arxiv.org
Foundation models have shown impressive adaptation and scalability in supervised and self-
supervised learning problems, but so far these successes have not fully translated to …

Human-timescale adaptation in an open-ended task space

J Bauer, K Baumli, F Behbahani… - International …, 2023‏ - proceedings.mlr.press
Foundation models have shown impressive adaptation and scalability in supervised and self-
supervised learning problems, but so far these successes have not fully translated to …

Towards generalist robot learning from internet video: A survey

R McCarthy, DCH Tan, D Schmidt, F Acero… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Scaling deep learning to massive, diverse internet data has yielded remarkably general
capabilities in visual and natural language understanding and generation. However, data …

Craftax: A lightning-fast benchmark for open-ended reinforcement learning

M Matthews, M Beukman, B Ellis, M Samvelyan… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Benchmarks play a crucial role in the development and analysis of reinforcement learning
(RL) algorithms. We identify that existing benchmarks used for research into open-ended …

On the importance of exploration for generalization in reinforcement learning

Y Jiang, JZ Kolter, R Raileanu - Advances in Neural …, 2023‏ - proceedings.neurips.cc
Existing approaches for improving generalization in deep reinforcement learning (RL) have
mostly focused on representation learning, neglecting RL-specific aspects such as …

Open-endedness is essential for artificial superhuman intelligence

E Hughes, M Dennis, J Parker-Holder… - arxiv preprint arxiv …, 2024‏ - arxiv.org
In recent years there has been a tremendous surge in the general capabilities of AI systems,
mainly fuelled by training foundation models on internetscale data. Nevertheless, the …