Related papers: Eye of the Beholder: Improved Relation Generalizat…

Artificial intelligence systems increasingly involve continual learning to enable flexibility in general situations that are not encountered during system training. Human interaction with autonomous systems is broadly studied, but research…

Manipulation of deformable objects is a challenging task for a robot. It will be problematic to use a single sensory input to track the behaviour of such objects: vision can be subjected to occlusions, whereas tactile inputs cannot capture…

Reinforcement learning (RL) algorithms can find an optimal policy for a single agent to accomplish a particular task. However, many real-world problems require multiple agents to collaborate in order to achieve a common goal. For example, a…

Inspired by recent work in attention models for image captioning and question answering, we present a soft attention model for the reinforcement learning domain. This model uses a soft, top-down attention mechanism to create a bottleneck in…

Despite numerous successes, the field of reinforcement learning (RL) remains far from matching the impressive generalisation power of human behaviour learning. One possible way to help bridge this gap be to provide RL agents with richer,…

Unlike reinforcement learning (RL) agents, humans remain capable multitaskers in changing environments. In spite of only experiencing the world through their own observations and interactions, people know how to balance focusing on tasks…

Text-adventure games and text role-playing games are grand challenges for reinforcement learning game playing agents. Text role-playing games are open-ended environments where an agent must faithfully play a particular character. We…

The collaboration between agents has gradually become an important topic in multi-agent systems. The key is how to efficiently solve the credit assignment problems. This paper introduces MGAN for collaborative multi-agent reinforcement…

Reinforcement learning often uses neural networks to solve complex control tasks. However, neural networks are sensitive to input perturbations, which makes their deployment in safety-critical environments challenging. This work lifts…

Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize. We demonstrate that a trained agent fails completely when facing small visual changes, and that…

Achieving visual reasoning is a long-term goal of artificial intelligence. In the last decade, several studies have applied deep neural networks (DNNs) to the task of learning visual relations from images, with modest results in terms of…

Due to the realization that deep reinforcement learning algorithms trained on high-dimensional tasks can strongly overfit to their training environments, there have been several studies that investigated the generalization performance of…

Understanding physical phenomena is a key component of human intelligence and enables physical interaction with previously unseen environments. In this paper, we study how an artificial agent can autonomously acquire this intuition through…

Open ad hoc teamwork is the problem of training a single agent to efficiently collaborate with an unknown group of teammates whose composition may change over time. A variable team composition creates challenges for the agent, such as the…

Despite the significant progress of deep reinforcement learning (RL) in solving sequential decision making problems, RL agents often overfit to training environments and struggle to adapt to new, unseen environments. This prevents robust…

Common-sense physical reasoning is an essential ingredient for any intelligent agent operating in the real-world. For example, it can be used to simulate the environment, or to infer the state of parts of the world that are currently…

Most prior works on communication in multi-agent reinforcement learning have focused on emergent communication, which often results in inefficient and non-interpretable systems. Inspired by the role of language in natural intelligence, we…

In this work we present a technique to use natural language to help reinforcement learning generalize to unseen environments. This technique uses neural machine translation, specifically the use of encoder-decoder networks, to learn…

Recent advances at the intersection of reinforcement learning (RL) and visual intelligence have enabled agents that not only perceive complex visual scenes but also reason, generate, and act within them. This survey offers a critical and…

One of the most challenging aspects of real-world reinforcement learning (RL) is the multitude of unpredictable and ever-changing distractions that could divert an agent from what was tasked to do in its training environment. While an agent…