bbcc2af4
Explain use of epsilon in model embedding
7 年前
7d229e5c
Update Getting-Started-with-Balance-Ball.md
7 年前
3f85bb56
Merge branch 'master' into dev-broadcast
7 年前
46853a5a
Update installation.md
7 年前
aee5d336
Fix discrete state ( #33 )
* made BrainParameters a class to set default values
Modified the error message if the state is discrete
* Add discrete state support to PPO and provide discrete state example environment
* Add flexibility to continuous control as well
* Finish PPO flexible model generation implementation
* Fix formatting
* Support color observations
* Add best practices document
* bug fix for non square observations
* Update Readme.md
* Remove scipy dependency
* Add installation doc
7 年前
6cab43f9
Update Training-on-Amazon-Web-Service.md
7 年前
8071e029
Update Training-on-Amazon-Web-Service.md
7 年前
e0ef6921
Add pre-configured ami
7 年前
749481a1
Add connection timeout issue
7 年前
daf205da
Merge pull request #35 from Unity-Technologies/fix-docs
Move Wiki to Docs directory
7 年前
2ffa35ff
Update README.md
7 年前
15fea1be
Update README.md
7 年前
e22f7cc0
Update README.md
7 年前
52cc5322
Update README.md
7 年前
8e69382f
Update Using-TensorFlow-Sharp-in-Unity-(Experimental).md
7 年前
b01b4ec8
Update Unity-Agents-Overview.md
7 年前
8ee01348
Update Unity-Agents---Python-API.md
7 年前
587d3a62
Update Unity-Agents---Python-API.md
7 年前
4d984ec2
Update Unity-Agents---Python-API.md
7 年前
a298fb51
Update Training-on-Amazon-Web-Service.md
7 年前
7176176a
Update Organizing-the-Scene.md
7 年前
e479c6a6
Update Making-a-new-Unity-Environment.md
7 年前
fcca40cf
Update Getting-Started-with-Balance-Ball.md
7 年前
60f9d39f
Update Example-Environments.md
7 年前
59f68970
Update Agents-Editor-Interface.md
7 年前
fb595954
Update Agents-Editor-Interface.md
7 年前
c1abc3de
Update Agents-Editor-Interface.md
7 年前
108a28f2
Update Limitations-&-Common-Issues.md
7 年前
e78304a0
Update Using-TensorFlow-Sharp-in-Unity-(Experimental).md
7 年前
e3f2fbc3
Update Readme.md
7 年前
82086fdf
Update Unity-Agents-Overview.md
7 年前
0df8326e
minor fixes
7 年前
f97bcaee
Add .md to links
7 年前
4d3716fe
default discrete action is now 0
bug fix for discrete broadcast action (the action size should be one in Agents.cs)
modified Tennis so that the default action is no action
modified the TemplateDecsion.cs to ensure non null values are sent from Decide() and MakeMemory()
7 年前
15da5a71
Make home readme
7 年前
65df8ae9
fix on the instanciation of coreBrains,
fix on the conversion of actions to arrays in the BrainInfo received from step
7 年前
61740946
Move documentation to docs
7 年前
e191fbef
added warning in case no brins are set to external
7 年前
535efc4e
Merge pull request #27 from Unity-Technologies/fix-internal-placeholder
made a better error if a placeholder is missing or if a placeholder is …
7 年前
7118a209
bug fix : The environment only requests actions from external brains when unique
7 年前
f02f4f82
Merge pull request #28 from ASPePeX/housekeeping
Cleaned up the 3DBall example scene
7 年前
5db042c6
removed the broadcast checkbox
Added a Handshake method for the communicator
The academy will try to handshake regardless of the brains present
Player and Heuristic brains will send their information through the communicator but will not receive commands
7 年前
b393bcbf
renamed run to networkOutput
7 年前
0d82c458
Cleaned up the 3DBall example scene
7 年前
0c7debb9
Change tensorboard command to work on Windows
7 年前
e36b8bf0
added broadcast to the player and heuristic brain.
Allows the python API to record actions taken along with the states and rewards
7 年前
54d85928
made a nice error if a placeholder is missing or if a placeholder is not in the graph
7 年前
71591043
PPO additions and warnings
* Add linear decay to learning rate for PPO
* Add warning/exception for unsupported brain configurations w/ PPO
7 年前
2133d9cb
Remove scipy from requirements
7 年前
64037ccb
Merge pull request #16 from ASPePeX/keep-checkpoints
--keep-checkpoints=<n> option for ppo.py
7 年前
GitHub
vincentpierre
Arthur Juliani
Alexander Scheurer