Search Results for author:
Found 11 papers, 8 papers with code
Know When To Stop: A Study of Semantic Drift in Text Generation
Overall, our methods generalize and can be applied to any long-form text generation to produce more reliable information, by balancing trade-offs between factual accuracy, information quantity and computational cost.
Teaching Large Language Models to Reason with Reinforcement Learning
Surprisingly, we find the sample complexity of Expert Iteration is similar to that of PPO, requiring at most on the order of $10^6$ samples to converge from a pretrained checkpoint.
Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
As large language models (LLMs) become increasingly prevalent across many real-world applications, understanding and enhancing their robustness to user inputs is of paramount importance.
Generalization to New Sequential Decision Making Tasks with In-Context Learning
By training on large diverse offline datasets, our model is able to learn new MiniHack and Procgen tasks without any weight updates from just a handful of demonstrations.
Understanding the Effects of RLHF on LLM Generalisation and Diversity
OOD generalisation is crucial given the wide range of real-world scenarios in which these models are being used, while output diversity refers to the model's ability to generate varied outputs and is important for a variety of use cases.
LLaMA: Open and Efficient Foundation Language Models
We introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters.
Ranked #3 on
Question Answering
on OBQA
Dungeons and Data: A Large-Scale NetHack Dataset
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 environments and large-scale datasets.
Insights From the NeurIPS 2021 NetHack Challenge
In this report, we summarize the takeaways from the first NeurIPS 2021 NetHack Challenge.
moolib: A Platform for Distributed RL
Together with the moolib library, we present example user code which shows how moolib’s components can be used to implement common reinforcement learning agents as a simple but scalable distributed network of homogeneous peers.
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research
By leveraging the full set of entities and environment dynamics from NetHack, one of the richest grid-based video games, MiniHack allows designing custom RL testbeds that are fast and convenient to use.
GPflux: A Library for Deep Gaussian Processes
GPflux is compatible with and built on top of the Keras deep learning eco-system.
