Marathon Environments: Multi-Agent Continuous Control Benchmarks in a Modern Video Game Engine
Recent advances in deep reinforcement learning in the paradigm of locomotion using continuous control have raised the interest of game makers for the potential of digital actors using active ragdoll. Currently, the available options to develop these ideas are either researchers' limited codebase or proprietary closed systems. We present Marathon Environments, a suite of open source, continuous control benchmarks implemented on the Unity game engine, using the Unity ML- Agents Toolkit. We demonstrate through these benchmarks that continuous control research is transferable to a commercial game engine. Furthermore, we exhibit the robustness of these environments by reproducing advanced continuous control research, such as learning to walk, run and backflip from motion capture data; learning to navigate complex terrains; and by implementing a video game input control system. We show further robustness by training with alternative algorithms found in OpenAI.Baselines. Finally, we share strategies for significantly reducing the training time.
Code (1)
Tasks
continuous-controlContinuous ControlDeep Reinforcement LearningNavigateReinforcement LearningUnitySimilar Papers 제목 키워드 기반
SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?
AI agents are increasingly expected to complete long-horizon workflows that require sustained progress over hours, millions of tokens, and complex environments. Yet current agent benchmarks largely evaluate short-form ta…
Long-Context UnderstandingLeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalization
Long-horizon autoformalization of research mathematics fails not only at hard lemmas, but at scale: statements drift, dependencies tangle, context decays, and local repairs corrupt distant work. We present LeanMarathon, …
OS-Marathon: Benchmarking Computer-Use Agents on Long-Horizon Repetitive Tasks
Long-horizon, repetitive workflows are common in professional settings, such as processing expense reports from receipts and entering student grades from exam papers. These tasks are often tedious for humans since they c…
Marathon: A Race Through the Realm of Long Context with Large Language Models
With the advancement of large language models (LLMs) and the expansion of their context windows, existing long-context benchmarks fall short in effectively evaluating the models' comprehension and reasoning abilities in …
Long-Context UnderstandingMultiple-choiceMaking up for the deficit in a marathon run
To predict the final result of an athlete in a marathon run thoroughly is the eternal desire of each trainer. Usually, the achieved result is weaker than the predicted one due to the objective (e.g., environmental condit…