117 citations · 278 across the 28 of their papers we have counts for
30 papers
From AGI to ASI
Tim Genewein, Matija Franklin, Alexander Lerchner +11
Over the last decade, building human-level artificial general intelligence has moved from far-fetched speculation to being a concrete next-decade target for many of the largest AI…
Structure-Induced Information for Rerooting Levin Tree Search
Jake Tuero, Michael Buro, Laurent Orseau +1
Subgoal-based policy tree search, which uses a policy to guide search, is effective for complex single-agent deterministic problems but often relies on explicit subgoal generation…
Affordances Enable Partial World Modeling with LLMs
Khimya Khetarpal, Gheorghe Comanici, Jonathan Richens +5
Full models of the world require complex knowledge of immense detail. While pre-trained large models have been hypothesized to contain similar knowledge due to extensive pre-traini…
Understanding Prompt Tuning and In-Context Learning via Meta-Learning
Tim Genewein, Li Kevin Wenliang, Jordi Grau-Moya +3
Prompting is one of the main ways to adapt a pretrained model to target tasks. Besides manually constructing prompts, many prompt optimization methods have been proposed in the lit…
Exponential Speedups by Rerooting Levin Tree Search
Laurent Orseau, Marcus Hutter, Levi H. S. Lelis
Levin Tree Search (LTS) (Orseau et al., 2018) is a search algorithm for deterministic environments that uses a user-specified policy to guide the search. It comes with a formal gua…
Super-Exponential Regret for UCT, AlphaGo and Variants
Laurent Orseau, Remi Munos
We improve the proofs of the lower bounds of Coquelin and Munos (2007) that demonstrate that UCT can have regret (with exp terms) on the -chain…
Learning Universal Predictors
Jordi Grau-Moya, Tim Genewein, Marcus Hutter +8
Meta-learning has emerged as a powerful approach to train neural networks to learn new tasks quickly from limited data. Broad exposure to different tasks leads to versatile represe…
Finding Increasingly Large Extremal Graphs with AlphaZero and Tabu Search
Abbas Mehrabian, Ankit Anand, Hyunjik Kim +16
This work studies a central extremal graph theory problem inspired by a 1975 conjecture of Erdős, which aims to find graphs with a given size (number of nodes) that maximize the nu…
Language Modeling Is Compression
Grégoire Delétang, Anian Ruoss, Paul-Ambroise Duquenne +9
It has long been established that predictive models can be transformed into lossless compressors and vice versa. Incidentally, in recent years, the machine learning community has f…
Line Search for Convex Minimization
Laurent Orseau, Marcus Hutter
Golden-section search and bisection search are the two main principled algorithms for 1d minimization of quasiconvex (unimodal) functions. The first one only uses function queries,…
Levin Tree Search with Context Models
Laurent Orseau, Marcus Hutter, Levi H. S. Lelis
Levin Tree Search (LTS) is a search algorithm that makes use of a policy (a probability distribution over actions) and comes with a theoretical guarantee on the number of expansion…
Memory-Based Meta-Learning on Non-Stationary Distributions
Tim Genewein, Grégoire Delétang, Anian Ruoss +7
Memory-based meta-learning is a technique for approximating Bayes-optimal predictors. Under fairly general conditions, minimizing sequential prediction error, measured by the log l…
Proving Theorems using Incremental Learning and Hindsight Experience Replay
Eser Aygün, Laurent Orseau, Ankit Anand +5
Traditional automated theorem provers for first-order logic depend on speed-optimized search and many handcrafted heuristics that are designed to work best over a wide range of dom…
Isotuning With Applications To Scale-Free Online Learning
Laurent Orseau, Marcus Hutter
We extend and combine several tools of the literature to design fast, adaptive, anytime and scale-free online learning algorithms. Scale-free regret bounds must scale linearly with…
Training a First-Order Theorem Prover from Synthetic Data
Vlad Firoiu, Eser Aygun, Ankit Anand +6
A major challenge in applying machine learning to automated theorem proving is the scarcity of training data, which is a key ingredient in training successful deep learning models.…
Policy-Guided Heuristic Search with Guarantees
Laurent Orseau, Levi H. S. Lelis
The use of a policy and a heuristic function for guiding search can be quite effective in adversarial problems, as demonstrated by AlphaGo and its successors, which are based on th…
Avoiding Side Effects By Considering Future Tasks
Victoria Krakovna, Laurent Orseau, Richard Ngo +2
Designing reward functions is difficult: the designer has to specify what to do (what it means to complete the task) as well as what not to do (side effects that should be avoided…
Learning to Prove from Synthetic Theorems
Eser Aygün, Zafarali Ahmed, Ankit Anand +5
A major challenge in applying machine learning to automated theorem proving is the scarcity of training data, which is a key ingredient in training successful deep learning models.…
Logarithmic Pruning is All You Need
Laurent Orseau, Marcus Hutter, Omar Rivasplata
The Lottery Ticket Hypothesis is a conjecture that every large neural network contains a subnetwork that, when trained in isolation, achieves comparable performance to the large ne…
Iterative Budgeted Exponential Search
Malte Helmert, Tor Lattimore, Levi H. S. Lelis +2
We tackle two long-standing problems related to re-expansions in heuristic search algorithms. For graph search, A* can require expansions, where is the number of sta…
Zooming Cautiously: Linear-Memory Heuristic Search With Node Expansion Guarantees
Laurent Orseau, Levi H. S. Lelis, Tor Lattimore
We introduce and analyze two parameter-free linear-memory tree search algorithms. Under mild assumptions we prove our algorithms are guaranteed to perform only a logarithmic factor…
Soft-Bayes: Prod for Mixtures of Experts with Log-Loss
Laurent Orseau, Tor Lattimore, Shane Legg
We consider prediction with expert advice under the log-loss with the goal of deriving efficient and robust algorithms. We argue that existing algorithms such as exponentiated grad…
An investigation of model-free planning
Arthur Guez, Mehdi Mirza, Karol Gregor +10
The field of reinforcement learning (RL) is facing increasingly challenging domains with combinatorial complexity. For an RL agent to address these challenges, it is essential that…
Single-Agent Policy Tree Search With Guarantees
Laurent Orseau, Levi H. S. Lelis, Tor Lattimore +1
We introduce two novel tree search algorithms that use a policy to guide search. The first algorithm is a best-first enumeration that uses a cost function that allows us to prove a…