Search Results for author:
Found 19 papers, 11 papers with code
Social Choice for AI Alignment: Dealing with Diverse Human Feedback
Foundation models such as GPT-4 are fine-tuned to avoid unsafe or otherwise problematic behavior, so that, for example, they refuse to comply with requests for help with committing crimes or with producing racist text.
RewardBench: Evaluating Reward Models for Language Modeling
In this paper, we present RewardBench, a benchmark dataset and code-base for evaluation, to enhance scientific understanding of reward models.
A Survey on Data Selection for Language Models
A major factor in the recent success of large language models is the use of enormous and ever-growing text datasets for unsupervised pre-training.
OLMo: Accelerating the Science of Language Models
Given the importance of these details in scientifically studying these models, including their biases and potential risks, we believe it is essential for the research community to have access to powerful, truly open LMs.
Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research
Language models have become a critical technology to tackling a wide range of natural language processing tasks, yet many details about how the best-performing language models were developed are not reported.
Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2
Since the release of T\"ULU [Wang et al., 2023b], open resources for instruction tuning have developed quickly, from better base models to new finetuning techniques.
The Alignment Ceiling: Objective Mismatch in Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) more capable in complex settings.
Zephyr: Direct Distillation of LM Alignment
Starting from a dataset of outputs ranked by a teacher model, we apply distilled direct preference optimization (dDPO) to learn a chat model with significantly improved intent alignment.
A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning
Model-based Reinforcement Learning (MBRL) aims to make agents more sample-efficient, adaptive, and explainable by learning an explicit model of the environment.
BLISS: Interplanetary Exploration with Swarms of Low-Cost Spacecraft
Leveraging advancements in micro-scale technology, we propose a fleet of autonomous, low-cost, small solar sails for interplanetary exploration.
Measuring Data
We identify the task of measuring data to quantitatively characterize the composition of machine learning data and datasets.
Reward Reports for Reinforcement Learning
Building systems that are good for society in the face of complex societal effects requires a dynamic approach.
Investigating Compounding Prediction Errors in Learned Dynamics Models
In this paper, we explore the effects of subcomponents of a control problem on long term prediction error: including choosing a system, collecting data, and training a model.
Choices, Risks, and Reward Reports: Charting Public Policy for Reinforcement Learning Systems
In the long term, reinforcement learning (RL) is considered by many AI theorists to be the most promising path to artificial general intelligence.
The Challenges of Exploration for Offline Reinforcement Learning
Offline Reinforcement Learning (ORL) enablesus to separately study the two interlinked processes of reinforcement learning: collecting informative experience and inferring optimal behaviour.
On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning
We demonstrate that this problem can be tackled effectively with automated HPO, which we demonstrate to yield significantly improved performance compared to human experts.
Hyperparameter Optimization
Model-based Reinforcement Learning
+2
AI Development for the Public Interest: From Abstraction Traps to Sociotechnical Risks
Despite interest in communicating ethical problems and social contexts within the undergraduate curriculum to advance Public Interest Technology (PIT) goals, interventions at the graduate level remain largely unexplored.
Nonholonomic Yaw Control of an Underactuated Flying Robot with Model-based Reinforcement Learning
As a comparison to the significant engineering effort required for an analytic control law, we implement a data-driven model-based reinforcement learning yaw controller in a simulated flight task.
Robotics
Objective Mismatch in Model-based Reinforcement Learning
In our experiments, we study this objective mismatch issue and demonstrate that the likelihood of one-step ahead predictions is not always correlated with control performance.
Model-based Reinforcement Learning
reinforcement-learning
+1
