Related papers: Smaller Abstract State Spaces Enable Cross-Scale G…

As breakthroughs in deep learning transform key industries, models are increasingly required to extrapolate on datapoints found outside the range of the training set, a challenge we coin as out-of-support (OoS) generalisation. However,…

This paper concerns the central issues of model robustness and sample efficiency in offline reinforcement learning (RL), which aims to learn to perform decision making from history data without active exploration. Due to uncertainties and…

Reinforcement Learning (RL) is a learning paradigm concerned with learning to control a system so as to maximize an objective over the long term. This approach to learning has received immense interest in recent times and success manifests…

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…

We address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions, i.e. environments more general than (PO)MDPs. The task for an agent is to attain…

Several practical applications of reinforcement learning involve an agent learning from past data without the possibility of further exploration. Often these applications require us to 1) identify a near optimal policy or to 2) estimate the…

Large Language Model (LLM) agents are deployed in complex environments -- such as massive codebases, enterprise databases, and conversational histories -- where the relevant state far exceeds their context windows. To navigate these spaces,…

Partially observable Markov decision processes (POMDPs) are a general framework for sequential decision-making under latent state uncertainty, yet learning in POMDPs is intractable in the worst case. Motivated by sensing and probing…

This paper explores the impact of relational state abstraction on sample efficiency and performance in collaborative Multi-Agent Reinforcement Learning. The proposed abstraction is based on spatial relationships in environments where direct…

Out-of-distribution (OOD) generalisation is challenging because it involves not only learning from empirical data, but also deciding among various notions of generalisation, e.g., optimising the average-case risk, worst-case risk, or…

Hybrid Reinforcement Learning (RL), where an agent learns from both an offline dataset and online explorations in an unknown environment, has garnered significant recent interest. A crucial question posed by Xie et al. (2022) is whether…

The deployment of reinforcement learning (RL) in the real world comes with challenges in calibrating user trust and expectations. As a step toward developing RL systems that are able to communicate their competencies, we present a method of…

Modelling the behaviours of other agents is essential for understanding how agents interact and making effective decisions. Existing methods for agent modelling commonly assume knowledge of the local observations and chosen actions of the…

Abstraction of Markov Decision Processes is a useful tool for solving complex problems, as it can ignore unimportant aspects of an environment, simplifying the process of learning an optimal policy. In this paper, we propose a new algorithm…

Information theoretic sensor management approaches are an ideal solution to state estimation problems when considering the optimal control of multi-agent systems, however they are too computationally intensive for large state spaces,…

The recent progress in Reinforcement Learning applications to Resource Management presents MDPs without a deeper analysis of the impacts of design decisions on agent performance. In this paper, we compare and contrast four different MDP…

One of the significant challenges in reinforcement learning (RL) when dealing with noise is estimating latent states from observations. Causality provides rigorous theoretical support for ensuring that the underlying states can be uniquely…

Offline Reinforcement Learning (RL) suffers from the extrapolation error and value overestimation. From a generalization perspective, this issue can be attributed to the over-generalization of value functions or policies towards…

When playing video-games we immediately detect which entity we control and we center the attention towards it to focus the learning and reduce its dimensionality. Reinforcement Learning (RL) has been able to deal with big state spaces,…

Generalization to out-of-distribution (OOD) data is one of the central problems in modern machine learning. Recently, there is a surge of attempts to propose algorithms that mainly build upon the idea of extracting invariant features.…