125 citations · 206 across the 20 of their papers we have counts for
20 papers
Laguna M.1/XS.2 Technical Report
Julien Abadji, Marah Abdin, Connor Adams +93
We present Laguna M.1 and Laguna XS.2, two Mixture-of-Experts foundation models built for long-horizon, agentic coding: M.1 has B total parameters (B activated per tok…
WebGames: Challenging General-Purpose Web-Browsing AI Agents
George Thomas, Alex J. Chan, Jikun Kang +5
We introduce WebGames, a comprehensive benchmark suite designed to evaluate general-purpose web-browsing AI agents through a collection of 50+ interactive challenges. These challen…
LM2: Large Memory Models
Jikun Kang, Wenqi Wu, Filippos Christianos +5
This paper introduces the Large Memory Model (LM2), a decoder-only Transformer architecture enhanced with an auxiliary memory module that aims to address the limitations of standar…
Lightweight Neural App Control
Filippos Christianos, Georgios Papoudakis, Thomas Coste +3
This paper introduces a novel mobile phone control architecture, Lightweight Multi-modal App Control (LiMAC), for efficient interactions and control across various Android apps. Li…
Pangu-Agent: A Fine-Tunable Generalist Agent with Structured Reasoning
Filippos Christianos, Georgios Papoudakis, Matthieu Zimmer +13
A key method for creating Artificial Intelligence (AI) agents is Reinforcement Learning (RL). However, constructing a standalone RL policy that maps perception to action directly e…
Ask more, know better: Reinforce-Learned Prompt Questions for Decision Making with Large Language Models
Xue Yan, Yan Song, Xinyu Cui +4
Large language models (LLMs) demonstrate their promise in tackling complicated practical challenges by combining action-based policies with chain of thought (CoT) reasoning. Having…
Intrinsic Language-Guided Exploration for Complex Long-Horizon Robotic Manipulation Tasks
Eleftherios Triantafyllidis, Filippos Christianos, Zhibin Li
Current reinforcement learning algorithms struggle in sparse and complex environments, most notably in long-horizon manipulation tasks entailing a plethora of different sequences.…
SMAClite: A Lightweight Environment for Multi-Agent Reinforcement Learning
Adam Michalski, Filippos Christianos, Stefano V. Albrecht
There is a lack of standard benchmarks for Multi-Agent Reinforcement Learning (MARL) algorithms. The Starcraft Multi-Agent Challenge (SMAC) has been widely used in MARL research, b…
Revisiting the Gumbel-Softmax in MADDPG
Callum Rhys Tilbury, Filippos Christianos, Stefano V. Albrecht
MADDPG is an algorithm in multi-agent reinforcement learning (MARL) that extends the popular single-agent method, DDPG, to multi-agent scenarios. Importantly, DDPG is an algorithm…
Planning with Occluded Traffic Agents using Bi-Level Variational Occlusion Models
Filippos Christianos, Peter Karkus, Boris Ivanovic +2
Reasoning with occluded traffic agents is a significant open challenge for planning for autonomous vehicles. Recent deep learning models have shown impressive results for predictin…
Pareto Actor-Critic for Equilibrium Selection in Multi-Agent Reinforcement Learning
Filippos Christianos, Georgios Papoudakis, Stefano V. Albrecht
This work focuses on equilibrium selection in no-conflict multi-agent games, where we specifically study the problem of selecting a Pareto-optimal Nash equilibrium among several ex…
Deep Reinforcement Learning for Multi-Agent Interaction
Ibrahim H. Ahmed, Cillian Brewitt, Ignacio Carlucho +14
The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Tow…
Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learning
Lukas Schäfer, Filippos Christianos, Amos Storkey +1
Successful deployment of multi-agent reinforcement learning often requires agents to adapt their behaviour. In this work, we discuss the problem of teamwork adaptation in which a t…
Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration
Lukas Schäfer, Filippos Christianos, Josiah P. Hanna +1
Intrinsic rewards can improve exploration in reinforcement learning, but the exploration process may suffer from instability caused by non-stationary reward shaping and strong depe…
Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing
Filippos Christianos, Georgios Papoudakis, Arrasy Rahman +1
Sharing parameters in multi-agent deep reinforcement learning has played an essential role in allowing algorithms to scale to a large number of agents. Parameter sharing between ag…
Towards Open Ad Hoc Teamwork Using Graph-based Policy Learning
Arrasy Rahman, Niklas Höpner, Filippos Christianos +1
Ad hoc teamwork is the challenging problem of designing an autonomous agent which can adapt quickly to collaborate with teammates without prior coordination mechanisms, including j…
Agent Modelling under Partial Observability for Deep Reinforcement Learning
Georgios Papoudakis, Filippos Christianos, Stefano V. Albrecht
Modelling the behaviours of other agents is essential for understanding how agents interact and making effective decisions. Existing methods for agent modelling commonly assume kno…
Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks
Georgios Papoudakis, Filippos Christianos, Lukas Schäfer +1
Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used evaluation tasks and criteria, making comparisons between approaches difficult. In this work, we…
Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning
Filippos Christianos, Lukas Schäfer, Stefano V. Albrecht
Exploration in multi-agent reinforcement learning is a challenging problem, especially in environments with sparse rewards. We propose a general method for efficient exploration by…
Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning
Georgios Papoudakis, Filippos Christianos, Arrasy Rahman +1
Recent developments in deep reinforcement learning are concerned with creating decision-making agents which can perform well in various complex domains. A particular approach which…