Reinforcement-Learning

Offline Meta-Reinforcement Learning in Piecewise Stationary Environments

Contextual Latent World Models for Offline Meta Reinforcement Learning

Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data

Forgetting is Everywhere

We present a unified, algorithm-agnostic theory that defines forgetting as self-inconsistency in a learner’s predictive distribution—quantifying loss of predictive information—and …

Huawei-Edinburgh Joint Lab: Discrete Codebook World Models

Discrete Codebook World Models for Continuous Control

Aidan Scannell

• 28 Jan, 2025 • 1 min read

Read more

Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning

Discrete Codebook World Models

In reinforcement learning (RL), world models serve as internal simulators, enabling agents to predict environment dynamics and future outcomes in order to make informed decisions. …

Nordic AI Meet & AI Day: Sample-efficient Reinforcement Learning with Implicitly Quantized Representations

iQRL: Implicitly Quantized Representations for Sample-Efficient Reinforcement Learning

I will be presenting our research on self-supervised representation learning for reinforcement learning at the [International Workshop of Intelligent Autonomous Learning Systems …