Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
duo-ai 1.0.0 documentation
Logo
duo-ai 1.0.0 documentation
  • Quickstart
  • Core concepts
    • Problem setting
    • Main classes
    • Configuration
  • Tutorials
    • Train an agent with PPO
    • Train a coordination policy
    • Add a new environment
    • Add a new algorithm
  • Algorithms
    • Always
    • Logit Algorithms
    • Reinforcement Learning
    • PyOD (experimental)
    • Skyline
  • API reference
    • duo_ai
      • duo_ai.algorithms
        • duo_ai.algorithms.always
        • duo_ai.algorithms.logit
        • duo_ai.algorithms.ppo
        • duo_ai.algorithms.pyod
        • duo_ai.algorithms.random
      • duo_ai.core
        • duo_ai.core.algorithm
        • duo_ai.core.config
        • duo_ai.core.environment
        • duo_ai.core.evaluator
        • duo_ai.core.policy
      • duo_ai.environments
      • duo_ai.models
        • duo_ai.models.impala
        • duo_ai.models.ppo
      • duo_ai.policies
        • duo_ai.policies.always
        • duo_ai.policies.logit
        • duo_ai.policies.ppo
        • duo_ai.policies.pyod
        • duo_ai.policies.random
      • duo_ai.utils
        • duo_ai.utils.evaluation
        • duo_ai.utils.global_variables
        • duo_ai.utils.logging
        • duo_ai.utils.model
        • duo_ai.utils.wandb
Back to top
View this page

Core ConceptsΒΆ

  • Problem setting
    • 1. The YRC Problem
    • 2. The Coordinator
    • 3. The Coordination Environment (CoordEnv)
    • 4. Coordination Cost
    • 5. The YRC-0 Problem
  • Main classes
  • Configuration
Next
Problem setting
Previous
Quickstart
Copyright © 2025, Khanh Nguyen
Made with Sphinx and @pradyunsg's Furo