Related papers: Predictive Coding Enhances Meta-RL To Achieve Inte…
Learning good representations of historical contexts is one of the core challenges of reinforcement learning (RL) in partially observable environments. While self-predictive auxiliary tasks have been shown to improve performance in fully…
Unsupervised representation learning has succeeded with excellent results in many applications. It is an especially powerful tool to learn a good representation of environments with partial or noisy observations. In partially observable…
The ability to predict upcoming events has been hypothesized to comprise a key aspect of natural and machine cognition. This is supported by trends in deep reinforcement learning (RL), where self-supervised auxiliary objectives such as…
Learning effective representations in image-based environments is crucial for sample efficient Reinforcement Learning (RL). Unfortunately, in RL, representation learning is confounded with the exploratory experience of the agent -- learning…
Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make…
Self-supervised learning has become an increasingly important paradigm in the domain of machine intelligence. Furthermore, evidence for self-supervised adaptation, such as contrastive formulations, has emerged in recent computational…
Meta-reinforcement learning (meta-RL) algorithms enable agents to adapt quickly to tasks from few samples in dynamic environments. Such a feat is achieved through dynamic representations in an agent's policy network (obtained via reasoning…
Reinforcement Learning (RL) can enable agents to learn complex tasks. However, it is difficult to interpret the knowledge and reuse it across tasks. Inductive biases can address such issues by explicitly providing generic yet useful…
In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion…
Training objectives based on predictive coding have recently been shown to be very effective at learning meaningful representations from unlabeled speech. One example is Autoregressive Predictive Coding (Chung et al., 2019), which trains an…
In computational reinforcement learning, a growing body of work seeks to express an agent's model of the world through predictions about future sensations. In this manuscript we focus on predictions expressed as General Value Functions:…
Agents that interact with other agents often do not know a priori what the other agents' strategies are, but have to maximise their own online return while interacting with and learning about others. The optimal adaptive behaviour under…
Predictive coding is a message-passing framework initially developed to model information processing in the brain, and now also topic of research in machine learning due to some interesting properties. One of such properties is the natural…
While supervised learning has enabled great progress in many applications, unsupervised learning has not seen such widespread adoption, and remains an important and challenging endeavor for artificial intelligence. In this work, we propose…
Standard meta-learning for representation learning aims to find a common representation to be shared across multiple tasks. The effectiveness of these methods is often limited when the nuances of the tasks' distribution cannot be captured…
Meta reinforcement learning (RL) allows agents to leverage experience across a distribution of tasks on which the agent can train at will, enabling faster learning of optimal policies on new test tasks. Despite its success in improving…
Despite the broad application of deep reinforcement learning (RL), transferring and adapting the policy to unseen but similar environments is still a significant challenge. Recently, the language-conditioned policy is proposed to facilitate…
The success of Reinforcement Learning (RL) heavily relies on the ability to learn robust representations from the observations of the environment. In most cases, the representations learned purely by the reinforcement learning loss can…
The visual representation of a pre-trained model prioritizes the classifiability on downstream tasks, while the widespread applications for pre-trained visual models have posed new requirements for representation interpretability. However,…
High-dimensional observations are a major challenge in the application of model-based reinforcement learning (MBRL) to real-world environments. To handle high-dimensional sensory inputs, existing approaches use representation learning to…