Tensorforce
0.5.2
Basics
Installation
Getting started
Module specification
Features
run.py – Runner
tune.py – Hyperparameter tuner
Agents
Agent interface
Constant Agent
Random Agent
Tensorforce Agent
Deep Q-Network
Dueling DQN
Vanilla Policy Gradient
Actor-Critic
Advantage Actor-Critic
Deterministic Policy Gradient
Proximal Policy Optimization
Trust-Region Policy Optimization
Modules
Distributions
Layers
Memories
Networks
Objectives
Optimizers
Parameters
Preprocessing
Policies
Environments
Environment interface
Arcade Learning Environment
Maze Explorer
Open Sim
OpenAI Gym
OpenAI Retro
PyGame Learning Environment
ViZDoom
Tensorforce
Docs
»
Index
Edit on GitHub
Index
A
|
C
|
E
|
M
|
O
|
P
|
R
|
S
|
V
A
actions() (tensorforce.environments.Environment method)
ArcadeLearningEnvironment (class in tensorforce.environments)
C
close() (tensorforce.environments.Environment method)
create() (tensorforce.environments.Environment static method)
E
Environment (class in tensorforce.environments)
execute() (tensorforce.environments.Environment method)
M
max_episode_timesteps() (tensorforce.environments.Environment method)
MazeExplorer (class in tensorforce.environments)
O
OpenAIGym (class in tensorforce.environments)
OpenAIRetro (class in tensorforce.environments)
OpenSim (class in tensorforce.environments)
P
PyGameLearningEnvironment (class in tensorforce.environments)
R
reset() (tensorforce.environments.Environment method)
S
states() (tensorforce.environments.Environment method)
V
ViZDoom (class in tensorforce.environments)