reinforcement-learning

Discrete Codebook World Models for Continuous Control
In reinforcement learning (RL), world models serve as internal simulators, enabling agents to predict environment dynamics and future …
Aidan Scannell, Mohammadreza Nakhaei, Kalle Kujanpää, Yi Zhao, Kevin Luck, Arno Solin, Joni Pajarinen
PDF Cite Code Slides Video Website
Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning
Offline meta-reinforcement learning aims to equip agents with the ability to rapidly adapt to new tasks by training on data from a set …
Mohammadreza Nakhaei, Aidan Scannell, Joni Pajarinen
PDF Cite Code
Nordic AI Meet & AI Day: Sample-efficient Reinforcement Learning with Implicitly Quantized Representations
Oct 21, 2024 1:00 PM — Feb 13, 2023 12:30 PM Helsinki, Finland
Aidan Scannell
PDF Slides
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 2024.
Jul 23, 2024 2:50 PM — 3:05 PM Darmstädter Haus and Sporthotel Walliser, Kleinwalsertal, Austria
Aidan Scannell
PDF Poster Slides
iQRL: Implicitly Quantized Representations for Sample-Efficient Reinforcement Learning
Model-Based Reinforcement Learning
I’ll be giving a lecture on model-based RL at the Cambridge Ellis Unit Summer School on Probabilistic Machine Learning 2024.
Jul 17, 2024 11:30 AM — 1:00 PM University of Cambridge
Aidan Scannell
PDF Slides
Model-Based Reinforcement Learning
iQRL - Implicitly Quantized Representations for Sample-efficient Reinforcement Learning
Learning representations for reinforcement learning (RL) has shown much promise for continuous control. We propose an efficient …
Aidan Scannell, Kalle Kujanpää, Yi Zhao, Mohammadreza Nakhaei, Arno Solin, Joni Pajarinen
PDF Cite Website
iQRL - Implicitly Quantized Representations for Sample-efficient Reinforcement Learning
Quantized Representations Prevent Dimensional Collapse in Self-predictive RL
Learning representations for reinforcement learning (RL) has shown much promise for continuous control. We propose an efficient …
Aidan Scannell, Kalle Kujanpää, Yi Zhao, Mohammadreza Nakhaei, Arno Solin, Joni Pajarinen
Cite Website
Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning
Offline reinforcement learning (RL) allows learning sequential behavior from fixed datasets. Since offline datasets do not cover all …
Mohammadreza Nakhaei, Aidan Scannell, Joni Pajarinen
PDF Cite Code
Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning
Implicitly Quantized Representations for Reinforcement Learning
Learning representations for reinforcement learning (RL) has shown much promise for continuous control. In this project, we investigate using vector quantization to prevent representation collapse when learning representations for RL using a self-supervised latent-state consistency loss.
Aidan Scannell, Kalle Kujanpää, Yi Zhao, Mohammadreza Nakhaei, Arno Solin, Joni Pajarinen
PDF Code
Implicitly Quantized Representations for Reinforcement Learning
Function-Space Bayesian Deep Learning for Sequential Learning
Sequential learning paradigms pose challenges for gradient-based deep learning due to difficulties incorporating new data and retaining prior knowledge. While Gaussian processes elegantly tackle these problems, they struggle with scalability and handling rich inputs, such as images.
Aidan Scannell, Riccardo Mereu, Paul Chang, Ella Tamir, Joni Pajarinen, Arno Solin
PDF Code Website
Function-Space Bayesian Deep Learning for Sequential Learning