|
gptkbp:instance_of
|
gptkb:software
|
|
gptkbp:allows
|
multi-agent training
|
|
gptkbp:can_be_extended_by
|
custom environments
custom agents
|
|
gptkbp:can_be_used_with
|
gptkb:stadium
gptkb:Py_Torch
|
|
gptkbp:community_support
|
gptkb:archive
forums
|
|
gptkbp:developed_by
|
gptkb:Unity_Technologies
|
|
gptkbp:enables
|
real-time training
offline training
|
|
gptkbp:features
|
visual observations
continuous actions
discrete actions
vector observations
|
|
gptkbp:has
|
sample environments
|
|
gptkbp:has_documentation
|
online documentation
|
|
gptkbp:has_version
|
v1.0.0
v0.8.0
v0.5.0
v0.4.0
v0.6.0
v0.7.0
v0.9.0
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
ML-Agents Toolkit
|
|
gptkbp:includes
|
gptkb:Graphics_Processing_Unit
|
|
gptkbp:integrates_with
|
gptkb:Unity_Engine
|
|
gptkbp:is_compatible_with
|
gptkb:Tensor_Flow_2.x
Python 3.6 or later
Unity 2018.1 or later
|
|
gptkbp:is_open_source
|
gptkb:theorem
|
|
gptkbp:is_part_of
|
Unity ecosystem
|
|
gptkbp:is_used_for
|
interactive simulations
game AI development
training autonomous agents
training machine learning agents
|
|
gptkbp:is_used_in
|
gptkb:academic_research
game development
robotics research
simulation training
|
|
gptkbp:platform
|
gptkb:smartphone
gptkb:operating_system
|
|
gptkbp:provides
|
visualization tools
training algorithms
environment simulation
|
|
gptkbp:released_in
|
gptkb:2018
|
|
gptkbp:supports
|
reinforcement learning
curriculum learning
imitation learning
model loading
model saving
|
|
gptkbp:written_in
|
gptkb:Library
|
|
gptkbp:bfsParent
|
gptkb:aircraft
|
|
gptkbp:bfsLayer
|
3
|