|
gptkbp:instance_of
|
gptkb:Library
|
|
gptkbp:community_support
|
gptkb:true
|
|
gptkbp:developed_by
|
gptkb:C++
gptkb:Google
gptkb:Java_Script
|
|
gptkbp:enables
|
multi-agent scenarios
|
|
gptkbp:has
|
gptkb:robotics
atari
cartpole
gridworld
simple games
|
|
gptkbp:has_documentation
|
https://www.tensorflow.org/agents
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
TF Agents
|
|
gptkbp:includes
|
DDPG agent
DQN agent
PPO agent
SAC agent
|
|
gptkbp:is_compatible_with
|
TF 2.x
|
|
gptkbp:is_documented_in
|
gptkb:Read_The_Docs
gptkb:Git_Hub
|
|
gptkbp:is_open_source
|
gptkb:true
|
|
gptkbp:is_part_of
|
gptkb:machine_learning
gptkb:AI_technology
deep learning
Tensor Flow ecosystem
|
|
gptkbp:is_related_to
|
gptkb:Stable_Baselines
gptkb:RLlib
gptkb:gymnasium
gptkb:Py_Torch
gptkb:Ray
|
|
gptkbp:is_supported_by
|
gptkb:Google_Cloud
gptkb:Kaggle
Colab
|
|
gptkbp:is_used_by
|
gptkb:students
gptkb:developers
gptkb:researchers
|
|
gptkbp:is_used_in
|
academic papers
educational courses
industry projects
|
|
gptkbp:provides
|
gptkb:training
gptkb:Agent
policies
environments
Tensor Board integration
|
|
gptkbp:released_in
|
gptkb:2018
|
|
gptkbp:supports
|
gptkb:Tensor_Flow
custom environments
|
|
gptkbp:used_for
|
reinforcement learning
|
|
gptkbp:written_in
|
gptkb:Python
|
|
gptkbp:bfsParent
|
gptkb:Google_Brain_team
gptkb:Google_Brain
|
|
gptkbp:bfsLayer
|
4
|