7 papers
COMBAT: Conditional World Models for Behavioral Agent Training
Anmol Agarwal, Pranay Meshram, Sumer Singh +5
Recent advances in video generation have spurred the development of world models capable of simulating 3D-consistent environments and interactions with static objects. However, a s…
Results of the NeurIPS 2023 Neural MMO Competition on Multi-task Reinforcement Learning
Joseph Suárez, Kyoung Whan Choe, David Bloomin +22
We present the results of the NeurIPS 2023 Neural MMO Competition, which attracted over 200 participants and submissions. Participants trained goal-conditional policies that genera…
Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models
Alon Albalak, Duy Phung, Nathan Lile +8
Increasing interest in reasoning models has led math to become a prominent testing ground for algorithmic and methodological improvements. However, existing open math datasets eith…
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought
Violet Xiang, Charlie Snell, Kanishk Gandhi +11
We propose a novel framework, Meta Chain-of-Thought (Meta-CoT), which extends traditional Chain-of-Thought (CoT) by explicitly modeling the underlying reasoning required to arrive…
Generative Reward Models
Dakota Mahan, Duy Van Phung, Rafael Rafailov +6
Reinforcement Learning from Human Feedback (RLHF) has greatly improved the performance of modern Large Language Models (LLMs). The RLHF process is resource-intensive and technicall…
Self-Directed Synthetic Dialogues and Revisions Technical Report
Nathan Lambert, Hailey Schoelkopf, Aaron Gokaslan +3
Synthetic data has become an important tool in the fine-tuning of language models to follow instructions and solve complex problems. Nevertheless, the majority of open data to date…