Related papers: Where do goals come from? A Generic Approach to Au…

In goal-directed behavior, a large number of possible initial states end up in the pursued goal. The accompanying information loss implies that goal-oriented behavior is in one-to-one correspondence with an open subsystem whose entropy…

Most approaches for goal recognition rely on specifications of the possible dynamics of the actor in the environment when pursuing a goal. These specifications suffer from two key issues. First, encoding these dynamics requires careful…

Goal-conditioned reinforcement learning endows an agent with a large variety of skills, but it often struggles to solve tasks that require more temporally extended reasoning. In this work, we propose to incorporate imagined subgoals into…

Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve…

The space of human goals is tremendously vast; and yet, from just a few moments of watching a scene or reading a story, we seem to spontaneously infer a range of plausible motivations for the people and characters involved. What explains…

In the real world, linguistic agents are also embodied agents: they perceive and act in the physical world. The notion of Language Grounding questions the interactions between language and embodiment: how do learning agents connect or…

Building generalist agents that can accomplish many goals in rich open-ended environments is one of the research frontiers for reinforcement learning. A key limiting factor for building generalist agents with RL has been the need for a…

Reinforcement learning problems are often described through rewards that indicate if an agent has completed some task. This specification can yield desirable behavior, however many problems are difficult to specify in this manner, as one…

Humans and animals explore their environment and acquire useful skills even in the absence of clear goals, exhibiting intrinsic motivation. The study of intrinsic motivation in artificial agents is concerned with the following question:…

Recent advances in deep learning have brought attention to the possibility of creating advanced, general AI systems that outperform humans across many tasks. However, if these systems pursue unintended goals, there could be catastrophic…

A parameterized skill is a mapping from multiple goals/task parameters to the policy parameters to accomplish them. Existing works in the literature show how a parameterized skill can be learned given a task space that defines all the…

Understanding an agent's goals helps explain and predict its behaviour, yet there is no established methodology for reliably attributing goals to agentic systems. We propose a framework for evaluating goal-directedness that integrates…

Goals for reinforcement learning problems are typically defined through hand-specified rewards. To design such problems, developers of learning algorithms must inherently be aware of what the task goals are, yet we often require agents to…

In reinforcement learning, we often define goals by specifying rewards within desirable states. One problem with this approach is that we typically need to redefine the rewards each time the goal changes, which often requires some…

Intelligent agents need to select long sequences of actions to solve complex tasks. While humans easily break down tasks into subgoals and reach them through millions of muscle commands, current artificial intelligence is limited to tasks…

Transparency and explainability are important features that responsible autonomous vehicles should possess, particularly when interacting with humans, and causal reasoning offers a strong basis to provide these qualities. However, even if…

Learned world models summarize an agent's experience to facilitate learning complex behaviors. While learning world models from high-dimensional sensory inputs is becoming feasible through deep learning, there are many potential ways for…

We show that goal-directed action planning and generation in a teleological framework can be formulated using the free energy principle. The proposed model, which is built on a variational recurrent neural network model, is characterized by…

Can artificial agents learn to assist others in achieving their goals without knowing what those goals are? Generic reinforcement learning agents could be trained to behave altruistically towards others by rewarding them for altruistic…

While reinforcement learning provides an appealing formalism for learning individual skills, a general-purpose robotic system must be able to master an extensive repertoire of behaviors. Instead of learning a large collection of skills…