Related papers: Environmental drivers of systematicity and general…

Generalization in deep reinforcement learning over unseen environment variations usually requires policy learning over a large set of diverse training variations. We empirically observe that an agent trained on many variations (a…

Recent advances in artificial intelligence have been strongly driven by the use of game environments for training and evaluating agents. Games are often accessible and versatile, with well-defined state-transitions and goals allowing for…

Generalization is a major challenge for multi-agent reinforcement learning. How well does an agent perform when placed in novel environments and in interactions with new co-players? In this paper, we investigate and quantify the…

Many challenges remain before AI agents can be deployed in real-world environments. However, one virtue of such environments is that they are inherently multi-agent and contain human experts. Using advanced social intelligence in such an…

The recent successes of deep learning and deep reinforcement learning have firmly established their statuses as state-of-the-art artificial learning techniques. However, longstanding drawbacks of these approaches, such as their poor sample…

Humans represent scenes and objects in rich feature spaces, carrying information that allows us to generalise about category memberships and abstract functions with few examples. What determines whether a neural network model generalises…

A machine learning (ML) system must learn not only to match the output of a target function on a training set, but also to generalize to novel situations in order to yield accurate predictions at deployment. In most practical applications,…

Reinforcement learning agents often exhibit unintended goal-directed behaviour outside their training distribution, but we currently lack a principled understanding of how such agents will generalise to novel environments based on their…

Though deep reinforcement learning agents have achieved unprecedented success in recent years, their learned policies can be brittle, failing to generalize to even slight modifications of their environments or unfamiliar situations. The…

We explore the impact of environmental conditions on the competency of machine learning agents and how real-time competency assessments improve the reliability of ML agents. We learn a representation of conditions which impact the…

In this paper, we consider the problem of building learning agents that can efficiently learn to navigate in constrained environments. The main goal is to design agents that can efficiently learn to understand and generalize to different…

Deep reinforcement learning has the potential to train robots to perform complex tasks in the real world without requiring accurate models of the robot or its environment. A practical approach is to train agents in simulation, and then…

Systematic generalization aims to evaluate reasoning about novel combinations from known components, an intrinsic property of human cognition. In this work, we study systematic generalization of NNs in forecasting future time series of…

Learning to navigate in complex environments with dynamic elements is an important milestone in developing AI agents. In this work we formulate the navigation question as a reinforcement learning problem and show that data efficiency and…

Deep reinforcement learning has proven to be a great success in allowing agents to learn complex tasks. However, its application to actual robots can be prohibitively expensive. Furthermore, the unpredictability of human behavior in…

In continual learning (CL), an AI agent (e.g., autonomous vehicles or robotics) learns from non-stationary data streams under dynamic environments. For the practical deployment of such applications, it is important to guarantee robustness…

The last few years have witnessed substantial progress in the field of embodied AI where artificial agents, mirroring biological counterparts, are now able to learn from interaction to accomplish complex tasks. Despite this success,…

Supervised deep learning models require significant amount of labeled data to achieve an acceptable performance on a specific task. However, when tested on unseen data, the models may not perform well. Therefore, the models need to be…

Deciding whether an agent possesses a model of its surrounding world is a fundamental step toward understanding its capabilities and limitations. In [10], it was shown that, within a particular framework, every almost optimal and general…

Neural nets are powerful function approximators, but the behavior of a given neural net, once trained, cannot be easily modified. We wish, however, for people to be able to influence neural agents' actions despite the agents never training…