Related papers: Understanding Goal Generalisation in Sequential Re…

The question of whether deep neural networks are good at generalising beyond their immediate training experience is of critical importance for learning-based approaches to AI. Here, we consider tests of out-of-sample generalisation that…

The ability of an agent to do well in new environments is a critical aspect of intelligence. In machine learning, this ability is known as $\textit{strong}$ or $\textit{out-of-distribution}$ generalization. However, merely considering…

Passive observational data, such as human videos, is abundant and rich in information, yet remains largely untapped by current RL methods. Perhaps surprisingly, we show that passive data, despite not having reward or action labels, can…

Recently, empowered with the powerful capabilities of neural networks, reinforcement learning (RL) has successfully tackled numerous challenging tasks. However, while these models demonstrate enhanced decision-making abilities, they are…

General intelligence requires quick adaption across tasks. While existing reinforcement learning (RL) methods have made progress in generalization, they typically assume only distribution changes between source and target domains. In this…

Goals express agents' intentions and allow them to organize their behavior based on low-dimensional abstractions of high-dimensional world states. How can agents develop such goals autonomously? This paper proposes a detailed conceptual and…

Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought). Yet the mechanism by which sparse rewards drive policy…

In Reinforcement Learning (RL), the goal of agents is to discover an optimal policy that maximizes the expected cumulative rewards. This objective may also be viewed as finding a policy that optimizes a linear function of its state-action…

The main challenge of multiagent reinforcement learning is the difficulty of learning useful policies in the presence of other simultaneously learning agents whose changing behaviors jointly affect the environment's transition and reward…

Biological intelligence can learn to solve many diverse tasks in a data efficient manner by re-using basic knowledge and skills from one task to another. Furthermore, many of such skills are acquired without explicit supervision in an…

Reinforcement fine-tuning (RFT) has shown promise for training LLM agents to perform multi-turn decision-making based on environment feedback. However, most existing evaluations remain largely in-domain: training and testing are conducted…

Deep Reinforcement Learning (RL) is successful in solving many complex Markov Decision Processes (MDPs) problems. However, agents often face unanticipated environmental changes after deployment in the real world. These changes are often…

Learning agile humanoid behaviors from human motion offers a powerful route to natural, coordinated control, but existing approaches face a persistent trade-off: reference-tracking policies are often brittle outside the demonstration…

Recent developments in sequential experimental design look to construct a policy that can efficiently navigate the design space, in a way that maximises the expected information gain. Whilst there is work on achieving tractable policies for…

We present a novel, alternative framework for learning generative models with goal-conditioned reinforcement learning. We define two agents, a goal conditioned agent (GC-agent) and a supervised agent (S-agent). Given a user-input initial…

Reinforcement Learning (RL) agents often exhibit learning behaviors that are not intuitively interpretable by human observers, which can result in suboptimal feedback in collaborative teaching settings. Yet, how humans perceive and…

Building sample-efficient agents that generalize out-of-distribution (OOD) in real-world settings remains a fundamental unsolved problem on the path towards achieving higher-level cognition. One particularly promising approach is to begin…

Reinforcement learning agents tend to develop habits that are effective only under specific policies. Following an initial exploration phase where agents try out different actions, they eventually converge onto a particular policy. As this…

We study goal misgeneralization, a type of out-of-distribution generalization failure in reinforcement learning (RL). Goal misgeneralization failures occur when an RL agent retains its capabilities out-of-distribution yet pursues the wrong…

Deep reinforcement learning (RL) can acquire complex behaviors from low-level inputs, such as images. However, real-world applications of such methods require generalizing to the vast variability of the real world. Deep networks are known…