Search Results for author: Sebastian Flennerhag

Found 17 papers, 8 papers with code

Acceleration in Policy Optimization

no code implementations18 Jun 2023 Veronica Chelu, Tom Zahavy, Arthur Guez, Doina Precup, Sebastian Flennerhag

We work towards a unifying paradigm for accelerating policy optimization methods in reinforcement learning (RL) by integrating foresight in the policy improvement step via optimistic and adaptive updates.

Meta-Learning Policy Gradient Methods +1

Discovering Attention-Based Genetic Algorithms via Meta-Black-Box Optimization

1 code implementation8 Apr 2023 Robert Tjarko Lange, Tom Schaul, Yutian Chen, Chris Lu, Tom Zahavy, Valentin Dalibard, Sebastian Flennerhag

Genetic algorithms constitute a family of black-box optimization algorithms, which take inspiration from the principles of biological evolution.

Optimistic Meta-Gradients

no code implementations9 Jan 2023 Sebastian Flennerhag, Tom Zahavy, Brendan O'Donoghue, Hado van Hasselt, András György, Satinder Singh

We study the connection between gradient-based meta-learning and convex op-timisation.


Probing Transfer in Deep Reinforcement Learning without Task Engineering

no code implementations22 Oct 2022 Andrei A. Rusu, Sebastian Flennerhag, Dushyant Rao, Razvan Pascanu, Raia Hadsell

By formally organising these modifications into several factors of variation, we are able to show that Analyses of Variance (ANOVA) are a potent tool for studying the effects of human-relevant domain changes on the learning and transfer performance of a deep reinforcement learning agent.

reinforcement-learning Reinforcement Learning (RL) +1

Meta-Gradients in Non-Stationary Environments

no code implementations13 Sep 2022 Jelena Luketina, Sebastian Flennerhag, Yannick Schroecker, David Abel, Tom Zahavy, Satinder Singh

We support these results with a qualitative analysis of resulting meta-parameter schedules and learned functions of context features.

Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality

no code implementations26 May 2022 Tom Zahavy, Yannick Schroecker, Feryal Behbahani, Kate Baumli, Sebastian Flennerhag, Shaobo Hou, Satinder Singh

Finding different solutions to the same problem is a key aspect of intelligence associated with creativity and adaptation to novel situations.

Introducing Symmetries to Black Box Meta Reinforcement Learning

no code implementations22 Sep 2021 Louis Kirsch, Sebastian Flennerhag, Hado van Hasselt, Abram Friesen, Junhyuk Oh, Yutian Chen

We show that a recent successful meta RL approach that meta-learns an objective for backpropagation-based learning exhibits certain symmetries (specifically the reuse of the learning rule, and invariance to input and output permutations) that are not present in typical black-box meta RL systems.

Meta-Learning Meta Reinforcement Learning +2

Bootstrapped Meta-Learning

1 code implementation ICLR 2022 Sebastian Flennerhag, Yannick Schroecker, Tom Zahavy, Hado van Hasselt, David Silver, Satinder Singh

We achieve a new state-of-the art for model-free agents on the Atari ALE benchmark and demonstrate that it yields both performance and efficiency gains in multi-task meta-learning.

Efficient Exploration Few-Shot Learning +1

Discovering Diverse Nearly Optimal Policies with Successor Features

no code implementations ICML Workshop URL 2021 Tom Zahavy, Brendan O'Donoghue, Andre Barreto, Volodymyr Mnih, Sebastian Flennerhag, Satinder Singh

We propose Diverse Successive Policies, a method for discovering policies that are diverse in the space of Successor Features, while assuring that they are near optimal.

Temporal Difference Uncertainties as a Signal for Exploration

no code implementations5 Oct 2020 Sebastian Flennerhag, Jane X. Wang, Pablo Sprechmann, Francesco Visin, Alexandre Galashov, Steven Kapturowski, Diana L. Borsa, Nicolas Heess, Andre Barreto, Razvan Pascanu

Instead, we incorporate it as an intrinsic reward and treat exploration as a separate learning problem, induced by the agent's temporal difference uncertainties.

QuantNet: Transferring Learning Across Systematic Trading Strategies

2 code implementations7 Apr 2020 Adriano Koshiyama, Sebastian Flennerhag, Stefano B. Blumberg, Nick Firoozye, Philip Treleaven

The encoder transforms market-specific data into an abstract latent representation that is processed by a global model shared by all markets, while the decoder learns a market-specific trading strategy based on both local and global information from the market-specific encoder and the global model.

Meta-Learning Transfer Learning

Meta-Learning with Warped Gradient Descent

1 code implementation ICLR 2020 Sebastian Flennerhag, Andrei A. Rusu, Razvan Pascanu, Francesco Visin, Hujun Yin, Raia Hadsell

On the other hand, approaches that try to control a gradient-based update rule typically resort to computing gradients through the learning process to obtain their meta-gradients, leading to methods that can not scale beyond few-shot task adaptation.

Few-Shot Learning Inductive Bias

Augmenting correlation structures in spatial data using deep generative models

1 code implementation23 May 2019 Konstantin Klemmer, Adriano Koshiyama, Sebastian Flennerhag

We empirically show the superiority of this approach over conventional ensemble learning approaches and rivaling spatial data augmentation methods, using synthetic and real-world prediction tasks.

Data Augmentation Ensemble Learning

Transferring Knowledge across Learning Processes

4 code implementations ICLR 2019 Sebastian Flennerhag, Pablo G. Moreno, Neil D. Lawrence, Andreas Damianou

Approaches that transfer information contained only in the final parameters of a source model will therefore struggle.

Meta-Learning Transfer Learning

Breaking the Activation Function Bottleneck through Adaptive Parameterization

1 code implementation NeurIPS 2018 Sebastian Flennerhag, Hujun Yin, John Keane, Mark Elliot

Standard neural network architectures are non-linear only by virtue of a simple element-wise activation function, making them both brittle and excessively large.

Cannot find the paper you are looking for? You can Submit a new open access paper.