16 citations · 31 across the 8 of their papers we have counts for
9 papers
CWM: An Open-Weights LLM for Research on Code Generation with World Models
FAIR CodeGen team, Jade Copet, Quentin Carbonneaux +48
We release Code World Model (CWM), a 32-billion-parameter open-weights LLM, to advance research on code generation with world models. To improve code understanding beyond what can…
RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning
Jonas Gehring, Kunhao Zheng, Jade Copet +4
Large language models (LLMs) deployed as agents solve user-specified tasks over multiple steps while keeping the required manual engagement to a minimum. Crucially, such LLMs need…
Dungeons and Data: A Large-Scale NetHack Dataset
Eric Hambro, Roberta Raileanu, Danielle Rothermel +4
Recent breakthroughs in the development of agents to solve challenging sequential decision making problems such as Go, StarCraft, or DOTA, have relied on both simulated environment…
Insights From the NeurIPS 2021 NetHack Challenge
Eric Hambro, Sharada Mohanty, Dmitrii Babaev +26
In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge. Participants were tasked with developing a program or agent that can win (i.e., 'ascend' i…
Transfer of Fully Convolutional Policy-Value Networks Between Games and Game Variants
Dennis J. N. J. Soemers, Vegard Mella, Eric Piette +3
In this paper, we use fully convolutional architectures in AlphaZero-like self-play training setups to facilitate transfer between variants of board games as well as distinct games…
Deep Learning for General Game Playing with Ludii and Polygames
Dennis J. N. J. Soemers, Vegard Mella, Cameron Browne +1
Combinations of Monte-Carlo tree search and Deep Neural Networks, trained through self-play, have produced state-of-the-art results for automated game-playing in many board games.…
Polygames: Improved Zero Learning
Tristan Cazenave, Yen-Chi Chen, Guan-Wei Chen +21
Since DeepMind's AlphaZero, Zero learning quickly became the state-of-the-art method for many board games. It can be improved using a fully convolutional structure (no fully connec…
Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger
Gabriel Synnaeve, Zeming Lin, Jonas Gehring +5
We formulate the problem of defogging as state estimation and future state prediction from previous, partial observations in the context of real-time strategy games. We propose to…
High-Level Strategy Selection under Partial Observability in StarCraft: Brood War
Jonas Gehring, Da Ju, Vegard Mella +3
We consider the problem of high-level strategy selection in the adversarial setting of real-time strategy games from a reinforcement learning perspective, where taking an action co…