Statements (57)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:Library
|
| gptkbp:bfsLayer |
3
|
| gptkbp:bfsParent |
gptkb:Graphics_Processing_Unit
|
| gptkbp:developed_by |
gptkb:Job_Search_Engine
|
| gptkbp:enables |
distributed training
|
| gptkbp:facilitates |
experiment tracking
|
| gptkbp:has |
modular architecture
active community active development |
| https://www.w3.org/2000/01/rdf-schema#label |
Tensor Flow Agents
|
| gptkbp:includes |
actor-critic methods
policy gradient methods DDPG agent DQN agent PPO agent SAC agent Q-learning algorithms pre-built agents |
| gptkbp:is |
flexible
open-source scalable modular community-driven extensible widely used in industry suitable for beginners widely used in academia used for research used for financial modeling used for optimization problems used for robotics used for decision making suitable for experts used for simulations used for natural language processing compatible with Jupyter notebooks used for autonomous systems used for control tasks used for games used for healthcare applications used for production systems |
| gptkbp:is_used_for |
reinforcement learning
|
| gptkbp:offers |
customizable components
|
| gptkbp:part_of |
Tensor Flow ecosystem
|
| gptkbp:provides |
gptkb:document
environment wrappers example implementations high-level AP Is sample environments |
| gptkbp:released_in |
gptkb:2018
|
| gptkbp:supports |
gptkb:Python_3.x
gptkb:Tensor_Flow_2.x GPU acceleration Tensor Board integration multi-agent environments |
| gptkbp:utilizes |
Tensor Flow framework
|
| gptkbp:written_in |
gptkb:Library
|