Related papers: Information is Power: Intrinsic Control via Inform…

Inferring other agents' mental states such as their knowledge, beliefs and intentions is thought to be essential for effective interactions with other agents. Recently, multiagent systems trained via deep reinforcement learning have been…

In order for robots and other artificial agents to efficiently learn to perform useful tasks defined by an end user, they must understand not only the goals of those tasks, but also the structure and dynamics of that user's environment.…

Agents in real-world scenarios like automated driving deal with uncertainty in their environment, in particular due to perceptual uncertainty. Although, reinforcement learning is dedicated to autonomous decision-making under uncertainty…

Shannon's information entropy measures of the uncertainty of an event's outcome. If learning about a system reflects a decrease in uncertainty, then a plausible intuition is that learning should be accompanied by a decrease in the entropy…

Trajectory and control secrecy is an important issue in robotics security. This paper proposes a novel algorithm for the control input inference of a mobile agent without knowing its control objective. Specifically, the algorithm first…

The reasoning capabilities of embodied agents introduce a critical, under-explored inferential privacy challenge, where the risk of an agent generate sensitive conclusions from ambient data. This capability creates a fundamental tension…

Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures. Humans seem to learn rich representations by exploration and imitation, build causal models of…

This paper presents a theoretical framework unifying AIXI -- a model of universal AI -- with variational empowerment as an intrinsic drive for exploration. We build on the existing framework of Self-AIXI -- a universal learning agent that…

In this paper we introduce a new unsupervised reinforcement learning method for discovering the set of intrinsic options available to an agent. This set is learned by maximizing the number of different states an agent can reliably reach, as…

Effective exploration is critical for reinforcement learning agents in environments with sparse rewards or high-dimensional state-action spaces. Recent works based on state-visitation counts, curiosity and entropy-maximization generate…

Human language learners are exposed to a trickle of informative, context-sensitive language, but a flood of raw sensory data. Through both social language use and internal processes of rehearsal and practice, language learners are able to…

Although exploratory behaviors are ubiquitous in the animal kingdom, their computational underpinnings are still largely unknown. Behavioral Psychology has identified learning as a primary drive underlying many exploratory behaviors.…

A long-standing challenge in Reinforcement Learning is enabling agents to learn a model of their environment which can be transferred to solve other problems in a world with the same underlying rules. One reason this is difficult is the…

We study the statistical properties of trainable agents moving in discrete space. After introducing the mathematical framework, we first analyze the dynamics of two completely random walkers, mutually competing in a chaser-target…

Humans generally use natural language to communicate task requirements to each other. Ideally, natural language should also be usable for communicating goals to autonomous machines (e.g., robots) to minimize friction in task specification.…

In sequential machine teaching, a teacher's objective is to provide the optimal sequence of inputs to sequential learners in order to guide them towards the best model. In this paper we extend this setting from current static one-data-set…

The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group…

Reinforcement learning has the potential to automate the acquisition of behavior in complex settings, but in order for it to be successfully deployed, a number of practical challenges must be addressed. First, in real world settings, when…

Combining model-based and model-free deep reinforcement learning has shown great promise for improving sample efficiency on complex control tasks while still retaining high performance. Incorporating imagination is a recent effort in this…

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…