Related papers: Bootstrapped Representations in Reinforcement Lear…
We consider the general class of time-homogeneous stochastic dynamical systems, both discrete and continuous, and study the problem of learning a representation of the state that faithfully captures its dynamics. This is instrumental to…
Artificial neural systems trained using reinforcement, supervised, and unsupervised learning all acquire internal representations of high dimensional input. To what extent these representations depend on the different learning objectives is…
Offline reinforcement learning (RL) aims at learning policies from previously collected static trajectory data without interacting with the real environment. Recent works provide a novel perspective by viewing offline RL as a generic…
Continuous state spaces and stochastic, switching dynamics characterize a number of rich, realworld domains, such as robot navigation across varying terrain. We describe a reinforcementlearning algorithm for learning in these domains and…
Vision-based reinforcement learning (RL) is a promising approach to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image…
Sequential decision-making agents struggle with long horizon tasks, since solving them requires multi-step reasoning. Most reinforcement learning (RL) algorithms address this challenge by improved credit assignment, introducing memory…
We analyze the hidden activations of neural network policies of deep reinforcement learning (RL) agents and show, empirically, that it's possible to know a priori if a state representation will lend itself to fast learning. RL agents in…
Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from…
Machine learning approaches to spatiotemporal physical systems have primarily focused on next-frame prediction, with the goal of learning an accurate emulator for the system's evolution in time. However, these emulators are computationally…
In this paper we investigate the properties of representations learned by deep reinforcement learning systems. Much of the early work on representations for reinforcement learning focused on designing fixed-basis architectures to achieve…
Both animals and artificial agents benefit from state representations that support rapid transfer of learning across tasks and which enable them to efficiently traverse their environments to reach rewarding states. The successor…
We propose a multi-time-scale predictive representation learning method to efficiently learn robust driving policies in an offline manner that generalize well to novel road geometries, and damaged and distracting lane conditions which are…
Relational representations in reinforcement learning allow for the use of structural information like the presence of objects and relationships between them in the description of value functions. Through this paper, we show that such…
Deep reinforcement learning (RL) agents commonly rely on high-dimensional neural representations, despite growing evidence that task-relevant value and policy structure may be intrinsically low-dimensional. In this work, we present a simple…
Successor-style representations have many advantages for reinforcement learning: for example, they can help an agent generalize from past experience to new goals, and they have been proposed as explanations of behavioral and neural data…
Reinforcement learning systems have the potential to enable continuous improvement in unstructured environments, leveraging data collected autonomously. However, in practice these systems require significant amounts of instrumentation or…
In the field of reinforcement learning (RL), representation learning is a proven tool for complex image-based tasks, but is often overlooked for environments with low-level states, such as physical control problems. This paper introduces…
In this paper we introduce a simple approach for exploration in reinforcement learning (RL) that allows us to develop theoretically justified algorithms in the tabular case but that is also extendable to settings where function…
To achieve the ambitious goals of artificial intelligence, reinforcement learning must include planning with a model of the world that is abstract in state and time. Deep learning has made progress with state abstraction, but temporal…
Data-efficiency and generalization are key challenges in deep learning and deep reinforcement learning as many models are trained on large-scale, domain-specific, and expensive-to-label datasets. Self-supervised models trained on…