Out-of-distribution (OOD) generalisation is considered a hallmark of human and animal intelligence. To achieve OOD through composition, a system must discover the environment-invariant properties of experienced input-output mappings and transfer them to novel inputs. This can be realised if an intelligent system can identify appropriate, task-invariant, and composable input features, as well as the composition methods, thus allowing it to act based not on the interpolation between learnt data points but on the task-invariant composition of those features. We propose that in order to confirm that an algorithm does indeed learn compositional structures from data, it is not enough to just test on an OOD setup, but one also needs to confirm that the features identified are indeed compositional. We showcase this by exploring two tasks with clearly defined OOD metrics that are not OOD solvable by three commonly used neural networks: a Multi-Layer Perceptron (MLP), a Convolutional Neural Network (CNN), and a Transformer. In addition, we develop two novel network architectures imbued with biases that allow them to be successful in OOD scenarios. We show that even with correct biases and almost perfect OOD performance, an algorithm can still fail to learn the correct features for compositional generalisation.

The behavioural cloning (BC) paradigm has been the foundation of recent advances in robotic manipulation [1, 2]. BC is particularly promising for robot manipulation, as humans are very proficient in general manipulation, and can quickly learn to collect demonstrations when given a well-designed interface [3]. An important benefit of using this data to train a robot policy is that it can be collected on the real system, thus avoiding the sim-to-real gap. However, as a supervised learning method, BC requires the collected data to cover the workspace with relatively high density [4, 5, 6]. Neural networks trained with BC, and more generally functions estimated through supervised learning, hardly generalise outside the support of the training data, i.e. "out-of-distribution" (OOD) [7, 8].

Despite numerous successes, the field of reinforcement learning (RL) remains far from matching the impressive generalisation power of human behaviour learning. One possible way to help bridge this gap be to provide RL agents with richer, more human-like feedback expressed in natural language. To investigate this idea, we first extend BabyAI to automatically generate language feedback from the environment dynamics and goal condition success. Then, we modify the Decision Transformer architecture to take advantage of this additional signal. We find that training with language feedback either in place of or in addition to the return-to-go or goal descriptions improves agents' generalisation performance, and that agents can benefit from feedback even when this is only available during training, but not at inference.

Out-of-distribution (OOD) generalisation aims to build a model that can generalise well on an unseen target domain using knowledge from multiple source domains. To this end, the model should seek the causal dependence between inputs and labels, which may be determined by the semantics of inputs and remain invariant across domains. However, statistical or non-causal methods often cannot capture this dependence and perform poorly due to not considering spurious correlations learnt from model training via unobserved confounders. A well-known existing causal inference method like back-door adjustment cannot be applied to remove spurious correlations as it requires the observation of confounders. In this paper, we propose a novel method that effectively deals with hidden confounders by successfully implementing front-door adjustment (FA). FA requires the choice of a mediator, which we regard as the semantic information of images that helps access the causal mechanism without the need for observing confounders. Further, we propose to estimate the combination of the mediator with other observed images in the front-door formula via style transfer algorithms. Our use of style transfer to estimate FA is novel and sensible for OOD generalisation, which we justify by extensive experimental results on widely used benchmark datasets.