We present the Minigrid and Miniworld libraries which provide a suite of goal-oriented 2D
and 3D environments. The libraries were explicitly created with a minimalistic design …

The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to
produce RL algorithms whose policies generalise well to novel unseen situations at …

Training generally-capable agents with reinforcement learning (RL) remains a significant
challenge. A promising avenue for improving the robustness of RL agents is through the use …

Visual reinforcement learning (RL), which makes decisions directly from high-dimensional
visual inputs, has demonstrated significant potential in various domains. However …

Reinforcement learning methods trained on few environments rarely learn policies that
generalize to unseen environments. To improve generalization, we incorporate the inherent …

Given the input graph and its label/property, several key problems of graph learning, such as
finding interpretable subgraphs, graph denoising and graph compression, can be attributed …

Generalization is a central challenge for the deployment of reinforcement learning (RL)
systems in the real world. In this paper, we show that the sequential structure of the RL …

Many problems in RL, such as meta-RL, robust RL, generalization in RL, and temporal credit
assignment, can be cast as POMDPs. In theory, simply augmenting model-free RL with …

Deep reinforcement learning (RL) agents trained in a limited set of environments tend to
suffer overfitting and fail to generalize to unseen testing environments. To improve their …

Standard deep reinforcement learning algorithms use a shared representation for the policy
and value function, especially when training directly from images. However, we argue that …