Related papers: Semantic Curiosity for Active Visual Learning

Reinforcement learning with verifiable rewards (RLVR) has become a powerful paradigm for improving language models on reasoning-intensive tasks, but its effectiveness is often limited by exploration. For example, models often fail on hard…

Robots in many real-world settings have access to force/torque sensors in their gripper and tactile sensing is often necessary in tasks that involve contact-rich motion. In this work, we leverage surprise from mismatches in touch feedback…

Active learning for object detection is conventionally achieved by applying techniques developed for classification in a way that aggregates individual detections into image-level selection criteria. This is typically coupled with the…

Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both…

In Reinforcement Learning (RL), artificial agents are trained to maximize numerical rewards by performing tasks. Exploration is essential in RL because agents must discover information before exploiting it. Two rewards encouraging efficient…

Inference in natural language often involves recognizing lexical entailment (RLE); that is, identifying whether one word entails another. For example, "buy" entails "own". Two general strategies for RLE have been proposed: One strategy is…

Prior work has proposed a simple strategy for reinforcement learning (RL): label experience with the outcomes achieved in that experience, and then imitate the relabeled experience. These outcome-conditioned imitation learning methods are…

This paper considers the problem of efficient exploration of unseen environments, a key challenge in AI. We propose a `learning to explore' framework where we learn a policy from a distribution of environments. At test time, presented with…

This paper proposes a new active learning method for semantic segmentation. The core of our method lies in a new annotation query design. It samples informative local image regions (e.g., superpixels), and for each of such regions, asks an…

Active Geo-localization (AGL) is the task of localizing a goal, represented in various modalities (e.g., aerial images, ground-level images, or text), within a predefined search area. Current methods approach AGL as a goal-reaching…

Training robotic policies in simulation suffers from the sim-to-real gap, as simulated dynamics can be different from real-world dynamics. Past works tackled this problem through domain randomization and online system-identification. The…

We demonstrate the use of semantic object detections as robust features for Visual Teach and Repeat (VTR). Recent CNN-based object detectors are able to reliably detect objects of tens or hundreds of categories in a video at frame rates. We…

Offline reinforcement learning can enable policy learning from pre-collected, sub-optimal datasets without online interactions. This makes it ideal for real-world robots and safety-critical scenarios, where collecting online data or expert…

Reinforcement learning (RL) with sparse and deceptive rewards is challenging because non-zero rewards are rarely obtained. Hence, the gradient calculated by the agent can be stochastic and without valid information. Recent studies that…

This paper presents the first attempt to learn semantic boundary detection using image-level class labels as supervision. Our method starts by estimating coarse areas of object classes through attentions drawn by an image classification…

In real-world sequential decision making tasks like autonomous driving, robotics, and healthcare, learning from observed state-action trajectories is critical for tasks like imitation, classification, and clustering. For example,…

Most artificial neural networks used for object detection and recognition are trained in a fully supervised setup. This is not only very resource consuming as it requires large data sets of labeled examples but also very different from how…

Learning in sparse reward settings remains a challenge in Reinforcement Learning, which is often addressed by using intrinsic rewards. One promising strategy is inspired by human curiosity, requiring the agent to learn to predict the…

Rewards are sparse in the real world and most of today's reinforcement learning algorithms struggle with such sparsity. One solution to this problem is to allow the agent to create rewards for itself - thus making rewards dense and more…

Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment. However, in many tasks the…