Search Results for author:
Found 14 papers, 5 papers with code
Reinforced Self-Training (ReST) for Language Modeling
Reinforcement learning from human feedback (RLHF) can improve the quality of large language model's (LLM) outputs by aligning them with human preferences.
$\pi2\text{vec}$: Policy Representations with Successor Features
This paper describes $\pi2\text{vec}$, a method for representing behaviors of black box policies as feature vectors.
Vision-Language Models as Success Detectors
Detecting successful behaviour is crucial for training intelligent agents.
Retrieval-Augmented Reinforcement Learning
In this paper we explore an alternative paradigm in which we train a network to map a dataset of past experiences to optimal behavior.
Active Offline Policy Selection
We use multiple benchmarks, including real-world robotics, with a large number of candidate policies to show that the proposed approach improves upon state-of-the-art OPE estimates and pure online policy evaluation.
Semi-supervised reward learning for offline reinforcement learning
In offline reinforcement learning (RL) agents are trained using a logged dataset.
Offline Learning from Demonstrations and Unlabeled Experience
Behavior cloning (BC) is often practical for robot learning because it allows a policy to be trained offline without rewards, by supervised learning on expert demonstrations.
Scaling data-driven robotics with reward sketching and batch reinforcement learning
We present a framework for data-driven robotics that makes use of a large dataset of recorded robot experience and scales to several tasks using learned reward functions.
Discovering General-Purpose Active Learning Strategies
We propose a general-purpose approach to discovering active learning (AL) strategies from data.
Learning Intelligent Dialogs for Bounding Box Annotation
We demonstrate that (1) our agents are able to learn efficient annotation strategies in several scenarios, automatically adapting to the image difficulty, the desired quality of the boxes, and the detector strength; (2) in all scenarios the resulting annotation dialogs speed up annotation compared to manual box drawing alone and box verification alone, while also outperforming any fixed combination of verification and drawing in most scenarios; (3) in a realistic scenario where the detector is iteratively re-trained, our agents evolve a series of strategies that reflect the shifting trade-off between verification and drawing as the detector grows stronger.
Learning Active Learning from Data
In this paper, we suggest a novel data-driven approach to active learning (AL).
Geometry in Active Learning for Binary and Multi-class Image Segmentation
Our approach combines geometric smoothness priors in the image space with more traditional uncertainty measures to estimate which pixels or voxels are the most informative, and thus should to be annotated next.
God(s) Know(s): Developmental and Cross-Cultural Patterns in Children Drawings
This paper introduces a novel approach to data analysis designed for the needs of specialists in psychology of religion.
Introducing Geometry in Active Learning for Image Segmentation
We propose an Active Learning approach to training a segmentation classifier that exploits geometric priors to streamline the annotation process in 3D image volumes.
