281 citations · 389 across the 6 of their papers we have counts for
7 papers
Meta-Gradients in Non-Stationary Environments
Jelena Luketina, Sebastian Flennerhag, Yannick Schroecker +3
Meta-gradient methods (Xu et al., 2018; Zahavy et al., 2020) offer a promising solution to the problem of hyperparameter selection and adaptation in non-stationary reinforcement le…
WordCraft: An Environment for Benchmarking Commonsense Agents
Minqi Jiang, Jelena Luketina, Nantas Nardelli +4
The ability to quickly solve a wide range of real-world tasks requires a commonsense understanding of the world. Yet, how to best extract such knowledge from natural language corpo…
Transient Non-Stationarity and Generalisation in Deep Reinforcement Learning
Maximilian Igl, Gregory Farquhar, Jelena Luketina +2
Non-stationarity can arise in Reinforcement Learning (RL) even in stationary environments. For example, most RL algorithms collect new data throughout training, using a non-station…
A Survey of Reinforcement Learning Informed by Natural Language
Jelena Luketina, Nantas Nardelli, Gregory Farquhar +5
To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it…
Progress & Compress: A scalable framework for continual learning
Jonathan Schwarz, Jelena Luketina, Wojciech M. Czarnecki +4
We introduce a conceptually simple and scalable framework for continual learning domains where tasks are learned sequentially. Our method is constant in the number of parameters an…
On the Impossibility of Supersized Machines
Ben Garfinkel, Miles Brundage, Daniel Filan +6
In recent years, a number of prominent computer scientists, along with academics in fields such as philosophy and physics, have lent credence to the notion that machines may one da…
Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters
Jelena Luketina, Mathias Berglund, Klaus Greff +1
Hyperparameter selection generally relies on running multiple full training trials, with selection based on validation set performance. We propose a gradient-based approach for loc…