Documentation for For The Win (FTW) Agent implementation.

Components

• TensorFlow Modules & Networks
  • Subpackages
  • Auxiliary Task Modules & Networks
  • Distributional modules
  • Embedding Modules
  • For The Win (FTW) Network
  • Policy Value Head Module
  • Recurrent Core Modules
  • Vision (Visual Embedding) Modules
• For The Win (FTW) TensorFlow Agent
  • FTW Agent
  • FTW Learner
  • FTW Actor
• Utilities for Replay Buffers, Datasets, Hyperparameters & Internal Rewards
• Reverb Adders
  • Sequence Adder
  • Multi-Sequence Adder
  • Non-Overlapping RNN Sequence Adder
• Reverb Replay Datasets for TensorFlow
• Hyperparameters
  • Abstract Hyperparameter Class
  • Float Hyperparameter
  • Categorical Integer Hyperparameter
• Internal Rewards
  • Internal Rewards
• Environment Wrappers
  • Atari Convenience Functions
  • Multi-Agent Reinforcement Learning (MARL) Wrappers

Indices and tables

• Index
• Module Index
• Search Page