Tensorforce
stable

Basics

  • Installation
  • Getting started
  • Agent specification
  • Features
  • run.py – Runner
  • tune.py – Hyperparameter tuner

Agents

  • General agent interface
  • Constant Agent
  • Random Agent
  • Tensorforce Agent
  • Vanilla Policy Gradient
  • Proximal Policy Optimization
  • Trust-Region Policy Optimization
  • Deterministic Policy Gradient
  • Deep Q-Network
  • Double DQN
  • Dueling DQN
  • Actor-Critic
  • Advantage Actor-Critic

Modules

  • Distributions
  • Layers
  • Memories
  • Networks
  • Objectives
  • Optimizers
  • Parameters
  • Policies
  • Preprocessing

Execution

  • Runner utility

Environments

  • General environment interface
  • OpenAI Gym
  • Arcade Learning Environment
  • OpenAI Retro
  • Open Sim
  • PyGame Learning Environment
  • ViZDoom
Tensorforce
  • Docs »
  • Search
  • Edit on GitHub

© Copyright 2018, Tensorforce Team Revision 06173634.

Built with Sphinx using a theme provided by Read the Docs.