Related papers: Understanding and Controlling a Maze-Solving Polic…

Self-trained autonomous agents developed using machine learning are showing great promise in a variety of control settings, perhaps most remarkably in applications involving autonomous vehicles. The main challenge associated with…

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…

Reinforcement learning is a powerful technique to train an agent to perform a task. However, an agent that is trained using reinforcement learning is only capable of achieving the single task that is specified via its reward function. Such…

We train a single, goal-conditioned policy that can solve many robotic manipulation tasks, including tasks with previously unseen goals and objects. We rely on asymmetric self-play for goal discovery, where two agents, Alice and Bob, play a…

Our ability to predict the behavior of complex agents turns on the attribution of goals. Probing for goal-directed behavior comes in two flavors: Behavioral and mechanistic. The former proposes that goal-directedness can be estimated…

The problem of learning simultaneously several related tasks has received considerable attention in several domains, especially in machine learning with the so-called multitask learning problem or learning to learn problem [1], [2].…

Understanding a \textit{reinforcement learning} policy, which guides state-to-action mappings to maximize rewards, necessitates an accompanying explanation for human comprehension. In this paper, we introduce a set of \textit{linear…

Over the past decade, remarkable progress has been made in adopting deep neural networks to enhance the performance of conventional reinforcement learning. A notable milestone was the development of Deep Q-Networks (DQN), which achieved…

Policy learning for partially observed control tasks requires policies that can remember salient information from past observations. In this paper, we present a method for learning policies with internal memory for high-dimensional,…

This paper studies a class of multi-agent reinforcement learning (MARL) problems where the reward that an agent receives depends on the states of other agents, but the next state only depends on the agent's own current state and action. We…

Empowering embodied agents, such as robots, with Artificial Intelligence (AI) has become increasingly important in recent years. A major challenge is task open-endedness. In practice, robots often need to perform tasks with novel goals that…

Mechanistic interpretability (MI) aims to understand AI models by reverse-engineering the exact algorithms neural networks learn. Most works in MI so far have studied behaviors and capabilities that are trivial and token-aligned. However,…

The architecture of a neural network controlling an unknown environment is presented. It is based on a randomly connected recurrent neural network from which both perception and action are simultaneously read and fed back. There are two…

In certain situations, neural networks will represent environment states in their hidden activations. Our goal is to visualize what environment states the networks are representing. We experiment with a recurrent neural network (RNN)…

Multi-Agent Reinforcement Learning can lead to the development of collaborative agent behaviors that show similarities with organizational concepts. Pushing forward this perspective, we introduce a novel framework that explicitly…

Humans have come to rely on machines for reducing excessive information to manageable representations. But this reliance can be abused -- strategic machines might craft representations that manipulate their users. How can a user make good…

We develop a mathematical framework for solving multi-task reinforcement learning (MTRL) problems based on a type of policy gradient method. The goal in MTRL is to learn a common policy that operates effectively in different environments;…

Meta-learning is a branch of machine learning which aims to quickly adapt models, such as neural networks, to perform new tasks by learning an underlying structure across related tasks. In essence, models are being trained to learn new…

The demand for more transparency of decision-making processes of deep reinforcement learning agents is greater than ever, due to their increased use in safety critical and ethically challenging domains such as autonomous driving. In this…

Intelligent agents need to remember salient information to reason in partially-observed environments. For example, agents with a first-person view should remember the positions of relevant objects even if they go out of view. Similarly, to…