Search Results for author:
Found 17 papers, 7 papers with code
Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs
In systematic experimentation with controlled behavioral datasets, we find that priming Llama with examples containing these reasoning behaviors enables substantial improvements during RL, matching or exceeding Qwen's performance.
FSPO: Few-Shot Preference Optimization of Synthetic Preference Data in LLMs Elicits Effective Personalization to Real Users
Overall, FSPO achieves an 87% Alpaca Eval winrate on average in generating responses that are personalized to synthetic users and a 72% winrate with real human users in open-ended question answering.
Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models
However, existing open math datasets either contain a small collection of high-quality, human-written problems or a large corpus of machine-generated problems of uncertain quality, forcing researchers to choose between quality and quantity.
Personalized Preference Fine-tuning of Diffusion Models
With PPD, a diffusion model learns the individual preferences of a population of users in a few-shot way, enabling generalization to unseen users.
Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though
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 at a particular CoT.
Test-Time Alignment via Hypothesis Reweighting
Large pretrained models often struggle with underspecified tasks -- situations where the training data does not fully define the desired behavior.
Adaptive Inference-Time Compute: LLMs Can Predict if They Can Do Better, Even Mid-Generation
We further demonstrate that 50-75% of samples can be pruned early in generation with minimal degradation in performance.
D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning
However, evaluating progress on offline RL algorithms requires effective and challenging benchmarks that capture properties of real-world tasks, provide a range of task difficulties, and cover a range of challenges both in terms of the parameters of the domain (e. g., length of the horizon, sparsity of rewards) and the parameters of the data (e. g., narrow demonstration data or broad exploratory data).
Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
Our main finding is that, in general, approaches that use on-policy sampling or attempt to push down the likelihood on certain responses (i. e., employ a "negative gradient") outperform offline and maximum likelihood objectives.
Robotic Offline RL from Internet Videos via Value-Function Pre-Training
Our system, called V-PTR, combines the benefits of pre-training on video data with robotic offline RL approaches that train on diverse robot data, resulting in value functions and policies for manipulation tasks that perform better, act robustly, and generalize broadly.
RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
Our goal is to enable a single end-to-end trained model to both learn to map robot observations to actions and enjoy the benefits of large-scale pretraining on language and vision-language data from the web.
Ranked #4 on
Robot Manipulation
on SimplerEnv-Google Robot
(using extra training data)
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning
Our approach, calibrated Q-learning (Cal-QL), accomplishes this by learning a conservative value function initialization that underestimates the value of the learned policy from offline data, while also being calibrated, in the sense that the learned Q-values are at a reasonable scale.
Offline RL With Realistic Datasets: Heteroskedasticity and Support Constraints
Both theoretically and empirically, we show that typical offline RL methods, which are based on distribution constraints fail to learn from data with such non-uniform variability, due to the requirement to stay close to the behavior policy to the same extent across the state space.
Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials
To our knowledge, PTR is the first RL method that succeeds at learning new tasks in a new domain on a real WidowX robot with as few as 10 task demonstrations, by effectively leveraging an existing dataset of diverse multi-task robot data collected in a variety of toy kitchens.
When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?
To answer this question, we characterize the properties of environments that allow offline RL methods to perform better than BC methods, even when only provided with expert data.
Should I Run Offline Reinforcement Learning or Behavioral Cloning?
In this paper, our goal is to characterize environments and dataset compositions where offline RL leads to better performance than BC.
A Workflow for Offline Model-Free Robotic Reinforcement Learning
To this end, we devise a set of metrics and conditions that can be tracked over the course of offline training, and can inform the practitioner about how the algorithm and model architecture should be adjusted to improve final performance.
