Cover Image

Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Matthews, Michael, Beukman, Michael, Lu, Chris, Foerster, Jakob
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

JaxLife: An Open-Ended Agentic Simulator
by: Lu, Chris, et al.
Published: (2024)

JaxUED: A simple and useable UED library in Jax
by: Coward, Samuel, et al.
Published: (2024)

Goal-Conditioned Agents that Learn Everything All at Once
by: Matthews, Michael, et al.
Published: (2026)

Refining Minimax Regret for Unsupervised Environment Design
by: Beukman, Michael, et al.
Published: (2024)

No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery
by: Rutherford, Alexander, et al.
Published: (2024)

Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning
by: Matthews, Michael, et al.
Published: (2024)

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
by: Lu, Chris, et al.
Published: (2024)

DéjàQ: Open-Ended Evolution of Diverse, Learnable and Verifiable Problems
by: Röpke, Willem, et al.
Published: (2026)

Multi-Agent Craftax: Benchmarking Open-Ended Multi-Agent Reinforcement Learning at the Hyperscale
by: Omari, Bassel Al, et al.
Published: (2025)

Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
by: Samvelyan, Mikayel, et al.
Published: (2024)

Learning Multi-Agent Communication with Contrastive Learning
by: Lo, Yat Long, et al.
Published: (2023)

Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity
by: Costales, Robby, et al.
Published: (2024)

Policy-Guided Diffusion
by: Jackson, Matthew Thomas, et al.
Published: (2024)

Procedural Generation of Algorithm Discovery Tasks in Machine Learning
by: Goldie, Alexander D., et al.
Published: (2026)

Hierarchical Behaviour Spaces
by: Matthews, Michael Tryfan, et al.
Published: (2026)

Open-Endedness is Essential for Artificial Superhuman Intelligence
by: Hughes, Edward, et al.
Published: (2024)

The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning
by: Sims, Anya, et al.
Published: (2024)

Behaviour Distillation
by: Lupu, Andrei, et al.
Published: (2024)

A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem
by: Barde, Paul, et al.
Published: (2023)

Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
by: Liu, Zewen, et al.
Published: (2026)

Recurrent Reinforcement Learning with Memoroids
by: Morad, Steven, et al.
Published: (2024)

XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generation
by: Iyer, Vivek, et al.
Published: (2025)

Can Learned Optimization Make Reinforcement Learning Less Difficult?
by: Goldie, Alexander David, et al.
Published: (2024)

MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research
by: Chen, Hui, et al.
Published: (2025)

Foundation Model Self-Play: Open-Ended Strategy Innovation via Foundation Models
by: Dharna, Aaron, et al.
Published: (2025)

ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
by: Zhang, Qiang, et al.
Published: (2026)

SOLAR: A Self-Optimizing Open-Ended Autonomous Agent for Lifelong Learning and Continual Adaptation
by: Vetcha, Nitin, et al.
Published: (2026)

Discovering Temporally-Aware Reinforcement Learning Algorithms
by: Jackson, Matthew Thomas, et al.
Published: (2024)

From Classification to Generation: An Open-Ended Paradigm for Adverse Drug Reaction Prediction Based on Graph-Motif Feature Fusion
by: Pi, Yuyan, et al.
Published: (2026)

Goal Inference from Open-Ended Dialog
by: Ma, Rachel, et al.
Published: (2024)

AutoLibra: Agent Metric Induction from Open-Ended Human Feedback
by: Zhu, Hao, et al.
Published: (2025)

Evolving Many Worlds: Towards Open-Ended Discovery in Petri Dish NCA via Population-Based Training
by: Berdica, Uljad, et al.
Published: (2026)

Flexible Agent Alignment with Goal Inference from Open-Ended Dialog
by: Ma, Rachel, et al.
Published: (2025)

Open-Ended Task Discovery via Bayesian Optimization
by: Adachi, Masaki, et al.
Published: (2026)

Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments
by: Simmons-Edler, Riley, et al.
Published: (2025)

Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning
by: Ye, Zhiling, et al.
Published: (2025)

KASER: Knowledge-Aligned Student Error Simulator for Open-Ended Coding Tasks
by: Duan, Zhangqi, et al.
Published: (2026)

HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks
by: Wang, Zhilin, et al.
Published: (2025)

Task-agnostic Decision Transformer for Multi-type Agent Control with Federated Split Training
by: Wang, Zhiyuan, et al.
Published: (2024)

SOReL and TOReL: Two Methods for Fully Offline Reinforcement Learning
by: Fellows, Mattie, et al.
Published: (2025)