相关论文: Being curious about the answers to questions: nove…

We propose a novel attention model that can accurately attends to target objects of various scales and shapes in images. The model is trained to gradually suppress irrelevant regions in an input image via a progressive attentive process…

Two key challenges within Reinforcement Learning involve improving (a) agent learning within environments with sparse extrinsic rewards and (b) the explainability of agent actions. We describe a curious subgoal focused agent to address both…

Attentional Neural Network is a new framework that integrates top-down cognitive bias and bottom-up feature extraction in one coherent architecture. The top-down influence is especially effective when dealing with high noise or difficult…

An unaddressed challenge in multi-agent coordination is to enable AI agents to exploit the semantic relationships between the features of actions and the features of observations. Humans take advantage of these relationships in highly…

Biological infants are naturally curious and try to comprehend their physical surroundings by interacting, in myriad multisensory ways, with different objects - primarily macroscopic solid objects - around them. Through their various…

Sequence labeling architectures use word embeddings for capturing similarity, but suffer when handling previously unseen or rare words. We investigate character-level extensions to such models and propose a novel architecture for combining…

Camera equipped drones are nowadays being used to explore large scenes and reconstruct detailed 3D maps. When free space in the scene is approximately known, an offline planner can generate optimal plans to efficiently explore the scene.…

In correlation clustering, we are given $n$ objects together with a binary similarity score between each pair of them. The goal is to partition the objects into clusters so to minimise the disagreements with the scores. In this work we…

We apply recent advances in deep generative modeling to the task of imitation learning from biological agents. Specifically, we apply variations of the variational recurrent neural network model to a multi-agent setting where we learn…

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…

Hierarchical abstraction and curiosity-driven exploration are two common paradigms in current reinforcement learning approaches to break down difficult problems into a sequence of simpler ones and to overcome reward sparsity. However, there…

Many potential applications of reinforcement learning in the real world involve interacting with other agents whose numbers vary over time. We propose new neural policy architectures for these multi-agent problems. In contrast to other…

Traditional reinforcement learning agents learn from experience, past or present, gained through interaction with their environment. Our approach synthesizes experience, without requiring an agent to interact with their environment, by…

Visual attention is a mechanism closely intertwined with vision and memory. Top-down information influences visual processing through attention. We designed a neural network model inspired by aspects of human visual attention. This model…

Infants acquire language with generalization from minimal experience, whereas large language models require billions of training tokens. What underlies efficient development in humans? We investigated this problem through experiments…

Exploring the spectrum of novel behaviors a physical system can produce can be a labor-intensive task. Active learning is a collection of iterative sampling techniques developed in response to this challenge. However, these techniques often…

Animals exhibit an innate ability to learn regularities of the world through interaction. By performing experiments in their environment, they are able to discern the causal factors of variation and infer how they affect the world's…

We present an active visual search model for finding objects in unknown environments. The proposed algorithm guides the robot towards the sought object using the relevant stimuli provided by the visual sensors. Existing search strategies…

How do people actively learn to learn? That is, how and when do people choose actions that facilitate long-term learning and choosing future actions that are more informative? We explore these questions in the domain of active causal…

Attention mechanism is effective in both focusing the deep learning models on relevant features and interpreting them. However, attentions may be unreliable since the networks that generate them are often trained in a weakly-supervised…