Statements (68)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:Library
|
| gptkbp:bfsLayer |
3
|
| gptkbp:bfsParent |
gptkb:stadium
|
| gptkbp:based_on |
reinforcement learning principles
Tensor Flow framework |
| gptkbp:developed_by |
gptkb:Job_Search_Engine
|
| gptkbp:has_community |
tutorials
examples user forums active contributors |
| 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 T D3 agent |
| gptkbp:is_a_hub_for |
https://github.com/tensorflow/agents
|
| gptkbp:is_available_on |
gptkb:Py_PI
gptkb:archive |
| gptkbp:is_compatible_with |
gptkb:Unity_ML-Agents
gptkb:stadium |
| gptkbp:is_documented_in |
Tensor Flow documentation
|
| gptkbp:is_part_of |
open-source projects
machine learning frameworks AI development tools AI research tools |
| gptkbp:is_related_to |
gptkb:microprocessor
gptkb:Artificial_Intelligence gptkb:software_framework gptkb:robot algorithm development deep learning game development data science simulation environments optimization techniques exploration strategies reward systems state representation policy gradients value functions |
| gptkbp:is_supported_by |
gptkb:Tensor_Flow_team
|
| gptkbp:is_tested_for |
unit tests
performance benchmarks integration tests |
| gptkbp:is_used_for |
reinforcement learning
|
| gptkbp:is_used_in |
educational purposes
research projects industry applications |
| gptkbp:part_of |
Tensor Flow ecosystem
|
| gptkbp:provides |
gptkb:horse_race
gptkb:government_agency policies evaluation metrics experiments environments training loops observation and action spaces replay buffers |
| gptkbp:released_in |
gptkb:2018
|
| gptkbp:supports |
gptkb:Graphics_Processing_Unit
gptkb:Tensor_Flow_2.x GPU acceleration multi-agent systems distributed training custom environments |
| gptkbp:written_in |
gptkb:Library
|