Aidan Scannell
  • Home
  • Publications
  • Talks
  • Posts
  • Projects
  • Experience
  • CV
  • Notes
  • Notes
    • HPC Cluster
      • Cluster log in with SSH
      • Conda environments
      • Debugging on a cluster
      • Hydra submitit launcher
      • Running Jupyter Notebooks on GPU Clusters
    • .Dotfiles
      • Literate Dotfiles
      • Literate Emacs Configuration
    • Programming
      • Python
  • News
  • Projects
    • 1X World Model Challenge
    • Discrete Codebook World Models
    • Implicitly Quantized Representations for Reinforcement Learning
    • Function-Space Bayesian Deep Learning for Sequential Learning
    • Investigating Bayesian Neural Network Dynamics Models for Model-Based Reinforcement Learning
    • Mode-Constrained Exploration for Model-Based Reinforcement Learning
    • GPJax - Gaussian Processes in Jax
    • Trajectory Optimisation in Learned Multimodal Dynamical Systems
    • Identifiable Mixtures of Sparse Variational Gaussian Process Experts
    • Approximate Inference
    • Model-Based Reinforcement Learning with Gaussian Processes
    • Probabilistic Modelling
    • Uncertain Agentspeak
    • Amazon Picking Challenge
    • Autonomous Vehicle Lane Detection Software
    • Kidnapped Robot
    • Ultrasonic Non-Destructive Testing
    • UAV Swarm
  • Publications
    • Generative World Modelling for Humanoids: 1X World Model Challenge Technical Report
    • Efficient Reinforcement Learning by Guiding Generalist World Models with Non-Curated Data
    • Generalist World Model Pre-Training for Efficient Reinforcement Learning
    • Discrete Codebook World Models for Continuous Control
    • Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning
    • iQRL - Implicitly Quantized Representations for Sample-efficient Reinforcement Learning
    • Quantized Representations Prevent Dimensional Collapse in Self-predictive RL
    • Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning
    • Function-space Parameterization of Neural Networks for Sequential Learning
    • Sparse Function-space Representation of Neural Networks
    • Mode-constrained Model-based Reinforcement Learning via Gaussian Processes
    • PhD Thesis: Bayesian Learning for Control in Multimodal Dynamical Systems
    • Identifiable Mixtures of Sparse Variational Gaussian Process Experts
    • Trajectory Optimisation in Learned Multimodal Dynamical Systems via Latent-ODE Collocation
    • An example preprint / working paper
    • An example journal article
    • An example conference paper
  • Experience
  • Posts
    • One Keyboard to Rule Them All - I Built a Dactyl Manuform
    • Creating a CV/Resume in Org-Mode using LaTeX Templates
    • Setting Up an Emacs Playground on MacOS - Emacs Mac Port | Chemacs | Emacsclient | Spacemacs
    • How RSI Made Me a Better Developer
    • Gaussian Process Regression
    • Welcome to Emacs Anonymous, Sorry, My Blog
  • Recent & Upcoming Talks
    • Generative World Models for Games
    • Generative World Modelling for Humanoids: 1X World Model Challenge
    • Huawei-Edinburgh Joint Lab: Discrete Codebook World Models
    • Nordic AI Meet & AI Day: Sample-efficient Reinforcement Learning with Implicitly Quantized Representations
    • iQRL: Implicitly Quantized Representations for Sample-Efficient Reinforcement Learning
    • Model-Based Reinforcement Learning
    • (Function-space) Laplace Approximation for Bayesian Neural Networks
    • Neural Networks as Sparse Gaussian Processes for Sequential Learning
    • Model-based reinforcement learning under uncertainty
    • Model-based reinforcement learning under uncertainty: the importance of knowing what you don't know
    • Aalto RL Reading Club: Simplifying Model-Based RL: Learning Representations, Latent-Space Models, and Policies with One Objective
    • PhD Thesis: Bayesian Learning for Control in Multimodal Dynamical Systems
    • Trajectory Optimisation in Learned Multimodal Dynamical Systems via Latent-ODE Collocation
    • Synergising Bayesian Inference and Probabilistic Geometries for Robotic Control

iQRL: Implicitly Quantized Representations for Sample-Efficient Reinforcement Learning

23 Jul, 2024·
Aidan Scannell
· 0 min read
Slides PDF Poster
Last updated on 3 Oct, 2025
Reinforcement-Learning Machine-Learning Representation-Learning Self-Supervised-Learning
← Nordic AI Meet & AI Day: Sample-efficient Reinforcement Learning with Implicitly Quantized Representations 21 Oct, 2024
Model-Based Reinforcement Learning 17 Jul, 2024 →

© 2025 Aidan Scannell. This work is licensed under CC BY NC ND 4.0

Made with Hugo Blox — Open Source. Build yours →