Publications (21)
Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks
Neil Band, Tim G. J. Rudner, Qixuan Feng +6
Bayesian deep learning seeks to equip deep neural networks with the ability to precisely quantify their predictive uncertainty, and has promised to make deep learning more reliable…
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Gemini Team, Petko Georgiev, Ving Ian Lei +1132
In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over…
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?
Angelos Filos, Panagiotis Tigas, Rowan McAllister +3
Out-of-training-distribution (OOD) scenarios are a common challenge of learning agents at deployment, typically leading to arbitrary deductions and poorly-informed decisions. In pr…
Invariant Causal Prediction for Block MDPs
Amy Zhang, Clare Lyle, Shagun Sodhani +5
Generalization across environments is critical to the successful application of reinforcement learning algorithms to real-world challenges. In this paper, we consider the problem o…
In-context Reinforcement Learning with Algorithm Distillation
Michael Laskin, Luyu Wang, Junhyuk Oh +11
We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal seque…
Reinforcement Learning for Portfolio Management
Angelos Filos
In this thesis, we develop a comprehensive account of the expressive power, modelling efficiency, and performance advantages of so-called trading agents (i.e., Deep Soft Recurrent…
PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
Angelos Filos, Clare Lyle, Yarin Gal +3
We study reinforcement learning (RL) with no-reward demonstrations, a setting in which an RL agent has access to additional data from the interaction of other agents with the same…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
Gemini: A Family of Highly Capable Multimodal Models
Gemini Team, Rohan Anil, Sebastian Borgeaud +1340
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consist…
Combining Behaviors with the Successor Features Keyboard
Wilka Carvalho, Andre Saraiva, Angelos Filos +7
The Option Keyboard (OK) was recently proposed as a method for transferring behavioral knowledge across tasks. OK transfers knowledge by adaptively combining subsets of known behav…
On the Importance of Opponent Modeling in Auction Markets
Mahmoud Mahfouz, Angelos Filos, Cyrine Chtourou +5
The dynamics of financial markets are driven by the interactions between participants, as well as the trading mechanisms and regulatory frameworks that govern these interactions. D…
Model-Value Inconsistency as a Signal for Epistemic Uncertainty
Angelos Filos, Eszter Vértes, Zita Marinho +7
Using a model of the environment and a value function, an agent can construct many estimates of a state's value, by unrolling the model for different lengths and bootstrapping with…
Self-Consistent Models and Values
Gregory Farquhar, Kate Baumli, Zita Marinho +4
Learned models of the environment provide reinforcement learning (RL) agents with flexible ways of making predictions about the environment. In particular, models enable planning,…
ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages
Andrew Jesson, Chris Lu, Gunshi Gupta +4
This paper proposes a step toward approximate Bayesian inference in on-policy actor-critic deep reinforcement learning. It is implemented through three changes to the Asynchronous…
Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning
Zachary Nado, Neil Band, Mark Collier +23
High-quality estimates of uncertainty and robustness are crucial for numerous real-world applications, especially for deep learning which underlies many deployed ML systems. The ab…
QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results
Raghav Mehta, Angelos Filos, Ujjwal Baid +89
Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges.…
Uncertainty Evaluation Metric for Brain Tumour Segmentation
Raghav Mehta, Angelos Filos, Yarin Gal +1
In this paper, we develop a metric designed to assess and rank uncertainty measures for the task of brain tumour sub-tissue segmentation in the BraTS 2019 sub-challenge on uncertai…
A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks
Angelos Filos, Sebastian Farquhar, Aidan N. Gomez +6
Evaluation of Bayesian deep learning (BDL) methods is challenging. We often seek to evaluate the methods' robustness and scalability, assessing whether new tools give `better' unce…
Towards Inverse Reinforcement Learning for Limit Order Book Dynamics
Jacobo Roa-Vicens, Cyrine Chtourou, Angelos Filos +3
Multi-agent learning is a promising method to simulate aggregate competitive behaviour in finance. Learning expert agents' reward functions through their external demonstrations is…
Composing Task Knowledge with Modular Successor Feature Approximators
Wilka Carvalho, Angelos Filos, Richard L. Lewis +2
Recently, the Successor Features and Generalized Policy Improvement (SF&GPI) framework has been proposed as a method for learning, composing, and transferring predictive knowledge…
Generalizing from a few environments in safety-critical reinforcement learning
Zachary Kenton, Angelos Filos, Owain Evans +1
Before deploying autonomous agents in the real world, we need to be confident they will perform safely in novel situations. Ideally, we would expose agents to a very wide range of…