Search Results for author: Théophane Weber

Found 16 papers, 6 papers with code

Equivariant MuZero

no code implementations9 Feb 2023 Andreea Deac, Théophane Weber, George Papamakarios

Model-based reinforcement learning algorithms, such as the highly successful MuZero, aim to accomplish this by learning a world model.

Model-based Reinforcement Learning reinforcement-learning +2

Investigating the role of model-based learning in exploration and transfer

no code implementations8 Feb 2023 Jacob Walker, Eszter Vértes, Yazhe Li, Gabriel Dulac-Arnold, Ankesh Anand, Théophane Weber, Jessica B. Hamrick

Our results show that intrinsic exploration combined with environment models present a viable direction towards agents that are self-supervised and able to generalize to novel reward functions.

Transfer Learning

Large-Scale Retrieval for Reinforcement Learning

no code implementations10 Jun 2022 Peter C. Humphreys, Arthur Guez, Olivier Tieleman, Laurent SIfre, Théophane Weber, Timothy Lillicrap

Effective decision making involves flexibly relating past experiences and relevant contextual information to a novel situation.

Decision Making Offline RL +3

Procedural Generalization by Planning with Self-Supervised World Models

no code implementations ICLR 2022 Ankesh Anand, Jacob Walker, Yazhe Li, Eszter Vértes, Julian Schrittwieser, Sherjil Ozair, Théophane Weber, Jessica B. Hamrick

One of the key promises of model-based reinforcement learning is the ability to generalize using an internal model of the world to make predictions in novel environments and tasks.

 Ranked #1 on Meta-Learning on ML10 (Meta-test success rate (zero-shot) metric)

Benchmarking Meta-Learning +2

Credit Assignment Techniques in Stochastic Computation Graphs

no code implementations7 Jan 2019 Théophane Weber, Nicolas Heess, Lars Buesing, David Silver

Stochastic computation graphs (SCGs) provide a formalism to represent structured optimization problems arising in artificial intelligence, including supervised, unsupervised, and reinforcement learning.

reinforcement-learning Reinforcement Learning (RL)

Learning to Search with MCTSnets

2 code implementations ICML 2018 Arthur Guez, Théophane Weber, Ioannis Antonoglou, Karen Simonyan, Oriol Vinyals, Daan Wierstra, Rémi Munos, David Silver

They are most typically solved by tree search algorithms that simulate ahead into the future, evaluate future states, and back-up those evaluations to the root of a search tree.

Learning model-based planning from scratch

2 code implementations19 Jul 2017 Razvan Pascanu, Yujia Li, Oriol Vinyals, Nicolas Heess, Lars Buesing, Sebastien Racanière, David Reichert, Théophane Weber, Daan Wierstra, Peter Battaglia

Here we introduce the "Imagination-based Planner", the first model-based, sequential decision-making agent that can learn to construct, evaluate, and execute plans.

Continuous Control Decision Making

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