no code implementations • 4 Dec 2023 • Lukas Schäfer, Logan Jones, Anssi Kanervisto, Yuhan Cao, Tabish Rashid, Raluca Georgescu, Dave Bignell, Siddhartha Sen, Andrea Treviño Gavito, Sam Devlin
Video games have served as useful benchmarks for the decision making community, but going beyond Atari games towards training agents in modern games has been prohibitively expensive for the vast majority of the research community.
1 code implementation • 28 Mar 2023 • Ahana Ghosh, Sebastian Tschiatschek, Sam Devlin, Adish Singla
We introduce a scaffolding framework based on pop quizzes presented as multi-choice programming tasks.
no code implementations • 2 Mar 2023 • Stephanie Milani, Arthur Juliani, Ida Momennejad, Raluca Georgescu, Jaroslaw Rzpecki, Alison Shaw, Gavin Costello, Fei Fang, Sam Devlin, Katja Hofmann
We aim to understand how people assess human likeness in navigation produced by people and artificially intelligent (AI) agents in a video game.
no code implementations • 15 Feb 2023 • Mingfei Sun, Benjamin Ellis, Anuj Mahajan, Sam Devlin, Katja Hofmann, Shimon Whiteson
In this paper, we show that the trust region constraint over policies can be safely substituted by a trust-region-free constraint without compromising the underlying monotonic improvement guarantee.
1 code implementation • 30 Jan 2023 • Adam Jelley, Amos Storkey, Antreas Antoniou, Sam Devlin
We evaluate our approach on an adaptation of a comprehensive few-shot learning benchmark, Meta-Dataset, and demonstrate the benefits of POEM over other meta-learning methods at representation learning from partial observations.
1 code implementation • 25 Jan 2023 • Tim Pearce, Tabish Rashid, Anssi Kanervisto, Dave Bignell, Mingfei Sun, Raluca Georgescu, Sergio Valcarcel Macua, Shan Zheng Tan, Ida Momennejad, Katja Hofmann, Sam Devlin
This paper studies their application as observation-to-action models for imitating human behaviour in sequential environments.
1 code implementation • 20 Nov 2022 • Micah Carroll, Orr Paradise, Jessy Lin, Raluca Georgescu, Mingfei Sun, David Bignell, Stephanie Milani, Katja Hofmann, Matthew Hausknecht, Anca Dragan, Sam Devlin
Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks.
no code implementations • 28 Apr 2022 • Micah Carroll, Jessy Lin, Orr Paradise, Raluca Georgescu, Mingfei Sun, David Bignell, Stephanie Milani, Katja Hofmann, Matthew Hausknecht, Anca Dragan, Sam Devlin
Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks.
no code implementations • 31 Jan 2022 • Mingfei Sun, Vitaly Kurin, Guoqing Liu, Sam Devlin, Tao Qin, Katja Hofmann, Shimon Whiteson
Furthermore, we show that ESPO can be easily scaled up to distributed training with many workers, delivering strong performance as well.
no code implementations • 31 Jan 2022 • Mingfei Sun, Sam Devlin, Jacob Beck, Katja Hofmann, Shimon Whiteson
We present trust region bounds for optimizing decentralized policies in cooperative Multi-Agent Reinforcement Learning (MARL), which holds even when the transition dynamics are non-stationary.
1 code implementation • 11 Dec 2021 • Mingfei Sun, Sam Devlin, Katja Hofmann, Shimon Whiteson
Sample efficiency is crucial for imitation learning methods to be applicable in real-world applications.
1 code implementation • 30 Jul 2021 • Robert Loftin, Aadirupa Saha, Sam Devlin, Katja Hofmann
High sample complexity remains a barrier to the application of reinforcement learning (RL), particularly in multi-agent systems.
1 code implementation • 20 May 2021 • Sam Devlin, Raluca Georgescu, Ida Momennejad, Jaroslaw Rzepecki, Evelyn Zuniga, Gavin Costello, Guy Leroy, Ali Shaw, Katja Hofmann
A key challenge on the path to developing agents that learn complex human-like behavior is the need to quickly and accurately quantify human-likeness.
no code implementations • 26 Jan 2021 • William H. Guss, Mario Ynocente Castro, Sam Devlin, Brandon Houghton, Noboru Sean Kuno, Crissman Loomis, Stephanie Milani, Sharada Mohanty, Keisuke Nakata, Ruslan Salakhutdinov, John Schulman, Shinya Shiroshita, Nicholay Topin, Avinash Ummadisingu, Oriol Vinyals
Although deep reinforcement learning has led to breakthroughs in many difficult domains, these successes have required an ever-increasing number of samples, affording only a shrinking segment of the AI community access to their development.
no code implementations • 14 Jan 2021 • Paul Knott, Micah Carroll, Sam Devlin, Kamil Ciosek, Katja Hofmann, A. D. Dragan, Rohin Shah
We apply this methodology to build a suite of unit tests for the Overcooked-AI environment, and use this test suite to evaluate three proposals for improving robustness.
no code implementations • 11 Jan 2021 • Luisa Zintgraf, Sam Devlin, Kamil Ciosek, Shimon Whiteson, Katja Hofmann
The optimal adaptive behaviour under uncertainty over the other agents' strategies w. r. t.
no code implementations • 21 Dec 2020 • Jacopo Castellini, Sam Devlin, Frans A. Oliehoek, Rahul Savani
Policy gradient methods have become one of the most popular classes of algorithms for multi-agent reinforcement learning.
no code implementations • 1 Sep 2020 • Mikhail Jacob, Sam Devlin, Katja Hofmann
We compare with literature from the research community that address the challenges identified and conclude by highlighting promising directions for future research supporting agent creation in the games industry.
no code implementations • 6 Jul 2020 • Ruqi Zhang, Yingzhen Li, Christopher De Sa, Sam Devlin, Cheng Zhang
Variational inference (VI) plays an essential role in approximate Bayesian inference due to its computational efficiency and broad applicability.
2 code implementations • 15 Jun 2020 • Rika Antonova, Maksim Maydanskiy, Danica Kragic, Sam Devlin, Katja Hofmann
Our second contribution is a unifying mathematical formulation for learning latent relations.
no code implementations • 8 Jun 2020 • Daniel Hernandez, Kevin Denamganai, Sam Devlin, Spyridon Samothrakis, James Alfred Walker
They allow to verify and replicate existing findings, and to link is connected results.
no code implementations • ICLR 2020 • Jacob Beck, Kamil Ciosek, Sam Devlin, Sebastian Tschiatschek, Cheng Zhang, Katja Hofmann
In many partially observable scenarios, Reinforcement Learning (RL) agents must rely on long-term memory in order to learn an optimal policy.
1 code implementation • 27 Mar 2020 • Raluca D. Gaina, Sam Devlin, Simon M. Lucas, Diego Perez-Liebana
Game-playing Evolutionary Algorithms, specifically Rolling Horizon Evolutionary Algorithms, have recently managed to beat the state of the art in win rate across many video games.
1 code implementation • NeurIPS 2019 • Maximilian Igl, Kamil Ciosek, Yingzhen Li, Sebastian Tschiatschek, Cheng Zhang, Sam Devlin, Katja Hofmann
We discuss those differences and propose modifications to existing regularization techniques in order to better adapt them to RL.
no code implementations • pproximateinference AABI Symposium 2019 • Ruqi Zhang, Yingzhen Li, Chris De Sa, Sam Devlin, Cheng Zhang
Variational inference (VI) plays an essential role in approximate Bayesian inference due to its computational efficiency and general applicability.
no code implementations • 13 Mar 2019 • Kleanthis Malialis, Sam Devlin, Daniel Kudenko
These are learning time, scalability and decentralised coordination i. e. no communication between the learning agents.
2 code implementations • 23 Jan 2019 • Diego Perez-Liebana, Katja Hofmann, Sharada Prasanna Mohanty, Noburu Kuno, Andre Kramer, Sam Devlin, Raluca D. Gaina, Daniel Ionita
Learning in multi-agent scenarios is a fruitful research direction, but current approaches still show scalability problems in multiple games with general reward settings and different opponent types.
Multi-agent Reinforcement Learning reinforcement-learning +1
1 code implementation • 3 Aug 2018 • Timothy Atkinson, Hendrik Baier, Tara Copplestone, Sam Devlin, Jerry Swan
In 2016, 2017, and 2018 at the IEEE Conference on Computational Intelligence in Games, the authors of this paper ran a competition for agents that can play classic text-based adventure games.
no code implementations • ICLR 2018 • Dino S. Ratcliffe, Luca Citi, Sam Devlin, Udo Kruschwitz
Many deep reinforcement learning approaches use graphical state representations, this means visually distinct games that share the same underlying structure cannot effectively share knowledge.
no code implementations • 17 Nov 2017 • Victoria Hodge, Sam Devlin, Nick Sephton, Florian Block, Anders Drachen, Peter Cowling
Given the comparatively limited supply of professional data, a key question is thus whether mixed-rank match datasets can be used to create data-driven models which predict winners in professional matches and provide a simple in-game statistic for viewers and broadcasters.