RLgraph API Reference Documentation

• 1. RLgraph Core API
• 2. Space Classes and Space Utilities
  • 2.1. Space Base Class Reference
  • 2.2. Box Spaces
  • 2.3. Container Spaces
  • 2.4. Space Utilities
• 3. Agent Classes
  • 3.1. Agent Base Class Reference
  • 3.2. DQN Agent
  • 3.3. ApeX Agent
  • 3.4. IMPALA Agent
• 4. Components Reference
  • 4.1. Component Base Class Reference
  • 4.2. Action Adapters
    • 4.2.1. Action Adapter Base Class
    • 4.2.2. Dueling Action Adapter
    • 4.2.3. Baseline Action Adapter
  • 4.3. Distributions
    • 4.3.1. Distribution Base Class
    • 4.3.2. Normal Distribution
    • 4.3.3. Bernoulli Distribution
    • 4.3.4. Categorical Distribution
    • 4.3.5. Beta Distribution
  • 4.4. Explorations
    • 4.4.1. Exploration Base Class
    • 4.4.2. EpsilonExploration Helper Class
  • 4.5. Helper Components Reference
  • 4.6. Layer Classes
    • 4.6.1. Layer Base Class
    • 4.6.2. Preprocessing Layers
    • 4.6.3. Neural Network Layers
    • 4.6.4. String/Text Processing Layers
  • 4.7. Loss Functions
    • 4.7.1. Loss Function Base Class
    • 4.7.2. DQN Loss Function
    • 4.7.3. IMPALA Loss Function
  • 4.8. Memories
    • 4.8.1. Memory Base Class
    • 4.8.2. ReplayMemory
    • 4.8.3. PrioritizedReplay
    • 4.8.4. FIFOQueue
    • 4.8.5. QueueRunner
  • 4.9. Neural Networks
    • 4.9.1. Stack Class
    • 4.9.2. PreprocessorStack
    • 4.9.3. DictPreprocessorStack
    • 4.9.4. NeuralNetwork
    • 4.9.5. Policy
    • 4.9.6. ActorComponent
  • 4.10. Optimizers
    • 4.10.1. Optimizer Base Class
    • 4.10.2. Local Optimizer
    • 4.10.3. Horovod Optimizer
  • 4.11. RLgraph Components from Select Papers Reference
  • 4.12. Queues Reference
• 5. Environment Classes
  • 5.1. Environment Base Class Reference
  • 5.2. Random Environment
  • 5.3. GridWorld Environments
  • 5.4. OpenAI Gym Environments
  • 5.5. DeepMind Lab Environments