Workshop
Agent Learning in Open-Endedness Workshop
Minqi Jiang · Mikayel Samvelyan · Jack Parker-Holder · Mayalen Etcheverry · Yingchen Xu · Michael Dennis · Roberta Raileanu
Room 211 - 213
Fri 15 Dec, 7 a.m. PST
Open-ended learning (OEL) is receiving rapidly growing attention in recent years, as deep learning models become ever more adept at learning meaningful and useful behaviors from web-scale data. Improving the performance and generality of such models depends greatly on our ability to continue to collect new and useful training data. OEL systems co-evolve the learning agent (e.g. the model) with its environment or other sources of training data, resulting in the continued, active generation of new training data specifically useful for the current agent or model. Conceivably such OEL processes, if designed appropriately, can lead to models exhibiting increasingly general capabilities. However, it remains an open problem to produce a truly open-ended system in practice, one that endlessly generates meaningfully novel data. We hope our workshop provides a forum both for bridging knowledge across a diverse set of relevant fields as well as sparking new insights that can enable truly open-ended learning systems.
Schedule
Fri 7:00 a.m. - 7:00 a.m.
|
Introductory remarks
(
Introductory remarks
)
>
SlidesLive Video |
Minqi Jiang · Mikayel Samvelyan 🔗 |
Fri 7:00 a.m. - 7:30 a.m.
|
Is Simulation Dead?
(
Invited talk
)
>
SlidesLive Video |
Tim Rocktäschel 🔗 |
Fri 7:30 a.m. - 8:00 a.m.
|
Lisa Soros
(
Invited talk
)
>
SlidesLive Video |
Lisa Soros 🔗 |
Fri 8:00 a.m. - 8:30 a.m.
|
Adaptive Machines: Unleashing the Power of Evolutionary Reinforcement Learning for Versatile and Resilient Robotics
(
Invited talk
)
>
SlidesLive Video |
Antoine Cully 🔗 |
Fri 8:30 a.m. - 9:00 a.m.
|
Amorphous Fortress: Exploring Emergent Behavior in Open-Ended Simulations
(
Invited talk
)
>
SlidesLive Video |
M Charity 🔗 |
Fri 9:00 a.m. - 9:15 a.m.
|
WebArena: A Realistic Web Environment for Building Autonomous Agents
(
Spotlight talk
)
>
SlidesLive Video |
Shuyan Zhou 🔗 |
Fri 9:15 a.m. - 9:30 a.m.
|
OMNI: Open-endedness via Models of human Notions of Interestingness
(
Spotlight talk
)
>
SlidesLive Video |
Jenny Zhang 🔗 |
Fri 9:30 a.m. - 9:45 a.m.
|
Voyager: An Open-Ended Embodied Agent with Large Language Models
(
Spotlight talk
)
>
SlidesLive Video |
Guanzhi Wang 🔗 |
Fri 10:45 a.m. - 11:45 a.m.
|
Poster session
(
Poster session
)
>
|
🔗 |
Fri 11:45 a.m. - 12:15 p.m.
|
Abstraction and Analogy are the Keys to Robust, Open-Ended AI
(
Invited talk
)
>
SlidesLive Video |
Melanie Mitchell 🔗 |
Fri 12:15 p.m. - 12:45 p.m.
|
Open-Ended and AI-Generating Algorithms in the Era of Foundation
(
Invited talk
)
>
SlidesLive Video |
Jeff Clune 🔗 |
Fri 12:45 p.m. - 1:15 p.m.
|
Algorithmic Scenario Generation as Quality Diversity Optimization
(
Invited talk
)
>
SlidesLive Video |
Stefanos Nikolaidis 🔗 |
Fri 1:15 p.m. - 1:45 p.m.
|
Feryal Behbahani
(
Invited talk
)
>
SlidesLive Video |
Feryal Behbahani 🔗 |
Fri 1:45 p.m. - 2:00 p.m.
|
Motif: Intrinsic Motivation from Artificial Intelligence Feedback
(
Spotlight talk
)
>
SlidesLive Video |
Martin Klissarov · Pierluca D'Oro 🔗 |
Fri 2:00 p.m. - 2:15 p.m.
|
Eureka: Human-Level Reward Design via Coding Large Language Models
(
Spotlight talk
)
>
SlidesLive Video |
Jason Ma 🔗 |
Fri 2:15 p.m. - 2:30 p.m.
|
Quality Diversity through Human Feedback
(
Spotlight talk
)
>
SlidesLive Video |
Li Ding 🔗 |
Fri 2:30 p.m. -
|
Discussion Panel
(
Panel
)
>
SlidesLive Video |
Jeff Clune · Linxi Fan · M Charity · Antoine Cully · Stefanos Nikolaidis · Roberta Raileanu · Tim Rocktäschel 🔗 |
-
|
Noisy ZSC: Breaking The Common Knowledge Assumption In Zero-Shot Coordination Games ( Poster ) > link | Usman Anwar · Jia Wan · David Krueger · Jakob Foerster 🔗 |
-
|
Stackelberg Driver Model for Continual Policy Improvement in Scenario-Based Closed-Loop Autonomous Driving ( Poster ) > link | Haoyi Niu · Qimao Chen · Yingyue Li · Jianming HU 🔗 |
-
|
Syllabus: Curriculum Learning Made Easy ( Poster ) > link | Ryan Sullivan 🔗 |
-
|
Rethinking Teacher-Student Curriculum Learning under the Cooperative Mechanics of Experience ( Poster ) > link | Manfred Diaz · Liam Paull · Andrea Tacchetti 🔗 |
-
|
Multi-Agent Diagnostics for Robustness via Illuminated Diversity ( Poster ) > link | Mikayel Samvelyan · Davide Paglieri · Minqi Jiang · Jack Parker-Holder · Tim Rocktäschel 🔗 |
-
|
JARVIS-1: Open-Ended Multi-task Agents with Memory-Augmented Multimodal Language Models ( Poster ) > link | Zihao Wang · Shaofei Cai · Anji Liu · Xiaojian (Shawn) Ma · Yitao Liang 🔗 |
-
|
minimax: Efficient Baselines for Autocurricula in JAX ( Poster ) > link | Minqi Jiang · Michael Dennis · Edward Grefenstette · Tim Rocktäschel 🔗 |
-
|
ACES: generating diverse programming puzzles with autotelic language models and semantic descriptors ( Poster ) > link | Julien Pourcel · Cédric Colas · Pierre-Yves Oudeyer · Laetitia Teodorescu 🔗 |
-
|
On the importance of data collection for training general goal-reaching policies. ( Poster ) > link | Alexis Jacq · Manu Orsini · Gabriel Dulac-Arnold · Olivier Pietquin · Matthieu Geist · Olivier Bachem 🔗 |
-
|
LiFT: Unsupervised Reinforcement Learning with Foundation Models as Teachers ( Poster ) > link | Taewook Nam · Juyong Lee · Jesse Zhang · Sung Ju Hwang · Joseph Lim · Karl Pertsch 🔗 |
-
|
WebArena: A Realistic Web Environment for Building Autonomous Agents ( Spotlight ) > link |
12 presentersShuyan Zhou · Frank F. Xu · Hao Zhu · Xuhui Zhou · Robert Lo · Abishek Sridhar · Xianyi Cheng · Tianyue Ou · Yonatan Bisk · Daniel Fried · Uri Alon · Graham Neubig |
-
|
Motif: Intrinsic Motivation from Artificial Intelligence Feedback ( Spotlight ) > link | Martin Klissarov · Pierluca D'Oro · Shagun Sodhani · Roberta Raileanu · Pierre-Luc Bacon · Pascal Vincent · Amy Zhang · Mikael Henaff 🔗 |
-
|
DOGE: Domain Reweighting with Generalization Estimation ( Poster ) > link | Simin Fan · Matteo Pagliardini · Martin Jaggi 🔗 |
-
|
Voyager: An Open-Ended Embodied Agent with Large Language Models
(
Spotlight
)
>
link
SlidesLive Video |
Guanzhi Wang · Yuqi Xie · Yunfan Jiang · Ajay Mandlekar · Chaowei Xiao · Yuke Zhu · Linxi Fan · Animashree Anandkumar 🔗 |
-
|
Curriculum Learning for Cooperation in Multi-Agent Reinforcement Learning ( Poster ) > link | Rupali Bhati · Vijaya Sai Krishna Gottipati · Clodéric Mars · Matthew Taylor 🔗 |
-
|
Continual Driving Policy Optimization with Closed-Loop Individualized Curricula ( Poster ) > link | Haoyi Niu · Yizhou Xu · Xingjian Jiang · Jianming HU 🔗 |
-
|
Emergence of collective open-ended exploration from Decentralized Meta-Reinforcement learning ( Poster ) > link | Richard Bornemann · Gautier Hamon · Eleni Nisioti · Clément Moulin-Frier 🔗 |
-
|
Does behavioral diversity in intrinsic rewards help exploration? ( Poster ) > link | Aya Kayal · Eduardo Pignatelli · Laura Toni 🔗 |
-
|
OMNI: Open-endedness via Models of human Notions of Interestingness
(
Spotlight
)
>
link
SlidesLive Video |
Jenny Zhang · Joel Lehman · Kenneth Stanley · Jeff Clune 🔗 |
-
|
Objectives Are All You Need: Solving Deceptive Problems Without Explicit Diversity Maintenance ( Poster ) > link | Ryan Boldi · Li Ding · Lee Spector 🔗 |
-
|
SmartPlay : A Benchmark for LLMs as Intelligent Agents ( Poster ) > link | Yue Wu · Xuan Tang · Tom Mitchell · Yuanzhi Li 🔗 |
-
|
Learning to Act without Actions ( Poster ) > link | Dominik Schmidt · Minqi Jiang 🔗 |
-
|
Adaptive Coalition Structure Generation
(
Poster
)
>
link
SlidesLive Video |
Lucia Cipolina Kun · Ignacio Carlucho · Kalesha Bullard 🔗 |
-
|
MCU: A Task-centric Framework for Open-ended Agent Evaluation in Minecraft ( Poster ) > link | Haowei Lin · Zihao Wang · Jianzhu Ma · Yitao Liang 🔗 |
-
|
Exploration with Principles for Diverse AI Supervision ( Poster ) > link | Hao Liu · Matei A Zaharia · Pieter Abbeel 🔗 |
-
|
Toward Open-ended Embodied Tasks Solving
(
Poster
)
>
link
SlidesLive Video |
Wei Wang · Dongqi Han · Xufang Luo · Yifei Shen · Charles Ling · Boyu Wang · Dongsheng Li 🔗 |
-
|
Mastering Memory Tasks with World Models ( Poster ) > link | Mohammad Reza Samsami · Artem Zholus · Janarthanan Rajendran · Sarath Chandar 🔗 |
-
|
Mini-BEHAVIOR: A Procedurally Generated Benchmark for Long-horizon Decision-Making in Embodied AI ( Poster ) > link | Emily Jin · Jiaheng Hu · Zhuoyi Huang · Ruohan Zhang · Jiajun Wu · Fei-Fei Li · Roberto Martín-Martín 🔗 |
-
|
Quality-Diversity through AI Feedback
(
Poster
)
>
link
SlidesLive Video |
Herbie Bradley · Andrew Dai · Hannah Teufel · Jenny Zhang · Koen Oostermeijer · Marco Bellagente · Jeff Clune · Kenneth Stanley · Grégory Schott · Joel Lehman 🔗 |
-
|
Quality Diversity through Human Feedback ( Spotlight ) > link | Li Ding · Jenny Zhang · Jeff Clune · Lee Spector · Joel Lehman 🔗 |
-
|
Mix-ME: Quality-Diversity for Multi-Agent Learning ( Poster ) > link | Garðar Ingvarsson Juto · Mikayel Samvelyan · Manon Flageat · Bryan Lim · Antoine Cully · Tim Rocktäschel 🔗 |
-
|
What can AI Learn from Human Exploration? Intrinsically-Motivated Humans and Agents in Open-World Exploration ( Poster ) > link | Yuqing Du · Eliza Kosoy · Alyssa L Dayan · Maria Rufova · Alison Gopnik · Pieter Abbeel 🔗 |
-
|
How the level sampling process impacts zero-shot generalisation in deep reinforcement learning ( Poster ) > link | Samuel Garcin · James Doran · Shangmin Guo · Christopher G Lucas · Stefano Albrecht 🔗 |
-
|
Vision-Language Models as a Source of Rewards ( Poster ) > link |
24 presentersHarris Chan · Volodymyr Mnih · Feryal Behbahani · Michael Laskin · Luyu Wang · Fabio Pardo · Maxime Gazeau · Himanshu Sahni · Daniel Horgan · Kate Baumli · Yannick Schroecker · Stephen Spencer · Richie Steigerwald · John Quan · Gheorghe Comanici · Sebastian Flennerhag · Alexander Neitz · Lei Zhang · Tom Schaul · Satinder Singh · Clare Lyle · Tim Rocktäschel · Jack Parker-Holder · Kristian Holsheimer |
-
|
Discovering Temporally-Aware Reinforcement Learning Algorithms ( Poster ) > link | Matthew T Jackson · Chris Lu · Louis Kirsch · Robert Lange · Shimon Whiteson · Jakob Foerster 🔗 |
-
|
CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing ( Poster ) > link | Zhibin Gou · Zhihong Shao · Yeyun Gong · yelong shen · Yujiu Yang · Nan Duan · Weizhu Chen 🔗 |
-
|
RAVL: Reach-Aware Value Learning for the Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning ( Poster ) > link | Anya Sims · Cong Lu · Yee Whye Teh 🔗 |
-
|
Improving Intrinsic Exploration by Creating Stationary Objectives
(
Poster
)
>
link
SlidesLive Video |
Roger Creus Castanyer · Joshua Romoff · Glen Berseth 🔗 |
-
|
Training Reinforcement Learning Agents and Humans with Difficulty-Conditioned Generators ( Poster ) > link | Sidney Tio · Pradeep Varakantham 🔗 |
-
|
Eureka: Human-Level Reward Design via Coding Large Language Models ( Spotlight ) > link | Jason Ma · William Liang · Guanzhi Wang · De-An Huang · Osbert Bastani · Dinesh Jayaraman · Yuke Zhu · Linxi Fan · Animashree Anandkumar 🔗 |
-
|
Quality Diversity in the Amorphous Fortress: Evolving for Complexity in 0-Player Games ( Poster ) > link | Sam Earle · M Charity · Julian Togelius · Dipika Rajesh 🔗 |
-
|
SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents ( Poster ) > link |
11 presentersXuhui Zhou · Hao Zhu · Leena Mathur · Ruohong Zhang · Haofei Yu · Zhengyang Qi · Louis-Philippe Morency · Yonatan Bisk · Daniel Fried · Graham Neubig · Maarten Sap |
-
|
HomeRobot: Open-Vocabulary Mobile Manipulation ( Poster ) > link |
18 presentersSriram Yenamandra · Arun Ramachandran · Karmesh Yadav · Austin Wang · Mukul Khanna · Theophile Gervet · Tsung-Yen Yang · Vidhi Jain · Alexander Clegg · John Turner · Zsolt Kira · Manolis Savva · Angel Chang · Devendra Singh Chaplot · Dhruv Batra · Roozbeh Mottaghi · Yonatan Bisk · Chris Paxton |
-
|
AgentTorch: Agent-based Modeling with Automatic Differentiation ( Poster ) > link | Ayush Chopra · Jayakumar Subramanian · Balaji Krishnamurthy · Ramesh Raskar 🔗 |
-
|
Diversity from Human Feedback
(
Poster
)
>
link
SlidesLive Video |
Ren-Jian Wang · Ke Xue · Yutong Wang · Peng Yang · Haobo Fu · Qiang Fu · Chao Qian 🔗 |
-
|
Unlocking the Power of Representations in Long-term Novelty-based Exploration ( Poster ) > link | Steven Kapturowski · Alaa Saade · Daniele Calandriello · Charles Blundell · Pablo Sprechmann · Leopoldo Sarra · Oliver Groth · Michal Valko · Bilal Piot 🔗 |
-
|
Diverse Offline Imitation Learning ( Poster ) > link | Marin Vlastelica Pogančić · Jin Cheng · Georg Martius · Pavel Kolev 🔗 |
-
|
From Centralized to Self-Supervised: Pursuing Realistic Multi-Agent Reinforcement Learning ( Poster ) > link | Violet Xiang · Logan Cross · Jan-Philipp Fraenken · Nick Haber 🔗 |
-
|
JaxMARL: Multi-Agent RL Environments in JAX ( Poster ) > link |
20 presentersAlexander Rutherford · Benjamin Ellis · Matteo Gallici · Jonathan Cook · Andrei Lupu · Garðar Ingvarsson Juto · Timon Willi · Akbir Khan · Christian Schroeder de Witt · Alexandra Souly · Saptarashmi Bandyopadhyay · Mikayel Samvelyan · Minqi Jiang · Robert Lange · Shimon Whiteson · Bruno Lacerda · Nick Hawes · Tim Rocktäschel · Chris Lu · Jakob Foerster |
-
|
CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization
(
Poster
)
>
link
SlidesLive Video |
Bodhisattwa Prasad Majumder · Bhavana Dalvi Mishra · Peter A Jansen · Oyvind Tafjord · Niket Tandon · Li Zhang · Chris Callison-Burch · Peter Clark 🔗 |
-
|
Skill-Conditioned Policy Optimization with Successor Features Representations ( Poster ) > link | Luca Grillotti · Maxence Faldor · Borja G. León · Antoine Cully 🔗 |
-
|
AssemblyCA: A Benchmark of Open-Endedness for Discrete Cellular Automata ( Poster ) > link | Keith Patarroyo · Abhishek Sharma · Sara Walker · Lee Cronin 🔗 |
-
|
PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice ( Poster ) > link | Joseph Suarez 🔗 |
-
|
t-DGR: A Trajectory-Based Deep Generative Replay Method for Continual Learning in Decision Making ( Poster ) > link | William Yue · Bo Liu · Peter Stone 🔗 |
-
|
Procedural generation of meta-reinforcement learning tasks ( Poster ) > link | Thomas Miconi 🔗 |
-
|
Curriculum Learning from Smart Retail Investors: Towards Financial Open-endedness ( Poster ) > link | Kent Wu · Ziyi Xia · Shuaiyu Chen · Xiao-Yang Liu 🔗 |
-
|
Melanie Mitchell
(
Invited
)
>
|
🔗 |