2 citations · 2 across the 12 of their papers we have counts for
12 papers
Benchmarking Open-Ended Multi-Agent Coordination in Language Agents
Kale-ab Abebe Tessera, Andras Szecsenyi, Cameron Barker +7
As language models are increasingly deployed as autonomous agents, they must coordinate with others over long horizons in open-ended interactive tasks. Yet existing evaluations rar…
Temporal Consistency Improves Generalization in Contextual Offline Meta Reinforcement Learning
Mohammadreza Nakheai, Aidan Scannell, Kevin Luck +1
Offline meta-reinforcement learning seeks to learn a policy that generalizes to new related tasks online. Context-based methods infer a task representation from transition historie…
Kalman Linear Attention: Parallel Bayesian Filtering For Efficient Language Modelling and State Tracking
Vaisakh Shaj, Cameron Barker, Aidan Scannell +3
State-space language models such as Mamba and gated linear attention (GLA) offer linear-complexity, parallelisable alternatives to transformers, but their linear state updates limi…
Forgetting is Everywhere
Ben Sanati, Thomas L. Lee, Trevor McInroe +4
A fundamental challenge in developing general learning algorithms is their tendency to forget past knowledge as they adapt to new data. Addressing this problem requires a principle…
Generative World Modelling for Humanoids: 1X World Model Challenge Technical Report
Riccardo Mereu, Aidan Scannell, Yuxin Hou +6
World models are a powerful paradigm in AI and robotics, enabling agents to reason about the future by predicting visual observations or compact latent states. The 1X World Model C…
Discrete Codebook World Models for Continuous Control
Aidan Scannell, Mohammadreza Nakhaei, Kalle Kujanpää +4
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.…
Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data
Yi Zhao, Aidan Scannell, Wenshuai Zhao +7
Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL). This paper expands the pool of usable data for offline-to-online…
Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning
Mohammadreza Nakhaei, Aidan Scannell, Joni Pajarinen
Offline meta-reinforcement learning aims to equip agents with the ability to rapidly adapt to new tasks by training on data from a set of different tasks. Context-based approaches…
Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning
Mohammadreza Nakhaei, Aidan Scannell, Joni Pajarinen
Offline reinforcement learning (RL) allows learning sequential behavior from fixed datasets. Since offline datasets do not cover all possible situations, many methods collect addit…
iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning
Aidan Scannell, Kalle Kujanpää, Yi Zhao +3
Learning representations for reinforcement learning (RL) has shown much promise for continuous control. We propose an efficient representation learning method using only a self-sup…
Function-space Parameterization of Neural Networks for Sequential Learning
Aidan Scannell, Riccardo Mereu, Paul Chang +3
Sequential learning paradigms pose challenges for gradient-based deep learning due to difficulties incorporating new data and retaining prior knowledge. While Gaussian processes el…
Sparse Function-space Representation of Neural Networks
Aidan Scannell, Riccardo Mereu, Paul Chang +3
Deep neural networks (NNs) are known to lack uncertainty estimates and struggle to incorporate new data. We present a method that mitigates these issues by converting NNs from weig…