Ervin Teng
|
f80b1d12
|
Use running norm and std
|
5 年前 |
|
Ervin Teng
|
0040dc7f
|
New way to update mean and var
|
5 年前 |
|
Ervin Teng
|
3d25f9d2
|
Merge branch 'master' into develop-agentprocessor
|
5 年前 |
|
Ervin Teng
|
0046ea2d
|
Add comment
|
5 年前 |
|
Ervin Teng
|
69e7eeac
|
Normalize based on number of elements
|
5 年前 |
|
Ervin Teng
|
8325b7e2
|
Revert gitignore
|
5 年前 |
GitHub
|
45010af3
|
Add stats reporter class and re-enable missing stats (#3076)
|
5 年前 |
|
Ervin Teng
|
4981c856
|
Fix mypy issue
|
5 年前 |
|
Ervin Teng
|
9e0ef912
|
Fixed value estimate bug
|
5 年前 |
|
Ervin Teng
|
400811b7
|
Remove defaultdict that didn't make sense
|
5 年前 |
|
Ervin Teng
|
d263d5be
|
Fix numpy import
|
5 年前 |
|
Ervin Teng
|
e577d5ea
|
Fix some mypy issues and remove unused code
|
5 年前 |
|
Ervin Teng
|
abc8ca9a
|
Fix tests
|
5 年前 |
|
Ervin Teng
|
1bd791e5
|
Merge branch 'master' into develop-agentprocessor
|
5 年前 |
|
Ervin Teng
|
bad47dad
|
Allow None max steps
|
5 年前 |
|
Ervin Teng
|
e2b2f4be
|
Address AgentProcessor comments
|
5 年前 |
|
Ervin Teng
|
ea49396a
|
Add docstring
|
5 年前 |
|
Ervin Teng
|
6242b67d
|
Add way to check if trajectory is done or max_reached
|
5 年前 |
|
Ervin Teng
|
fdf9aea7
|
Make conversion methods part of NamedTuples
|
5 年前 |
|
Ervin Teng
|
47f8fa7a
|
Fix some import errors
|
5 年前 |
|
Ervin Teng
|
c330f6f6
|
Merge branch 'master' into develop-agentprocessor
|
5 年前 |
|
Ervin Teng
|
9d1eff12
|
Fix one more np float32 issue
|
5 年前 |
|
Ervin Teng
|
77aea4cd
|
Fix np float32 errors
|
5 年前 |
|
Ervin Teng
|
2b811fc8
|
Properly report value estimates and episode length
|
5 年前 |
|
Ervin Teng
|
83126bb2
|
Fix PPO value tests
|
5 年前 |
|
Ervin Teng
|
43c0acfb
|
Fix test again
|
5 年前 |
|
Ervin Teng
|
77ff4822
|
Add back next_obs
|
5 年前 |
|
Ervin Teng
|
324d217b
|
Move agent_id to Trajectory
|
5 年前 |
|
Ervin Teng
|
97d66e71
|
Remove BootstrapExperience
|
5 年前 |
|
Ervin Teng
|
27c2a55b
|
Lots of test fixes
|
5 年前 |
|
Ervin Teng
|
38ff674e
|
Fix BC and tests
|
5 年前 |
|
Ervin Teng
|
3449b551
|
Add test for trajectory
|
5 年前 |
|
Ervin Teng
|
62d609f8
|
Fix some of the tests
|
5 年前 |
|
Ervin Teng
|
40bbe173
|
Better decoupling for agent processor
|
5 年前 |
|
Ervin Teng
|
5ab2563b
|
Fixes for recurrent
|
5 年前 |
|
Ervin Teng
|
c7632aa7
|
Fix some bugs for visual obs
|
5 年前 |
|
Ervin Teng
|
3697e616
|
Convert BC (warning) might be broken
|
5 年前 |
|
Ervin Teng
|
336ca456
|
Kill the ProcessingBuffer
|
5 年前 |
|
Ervin Teng
|
c9116ed2
|
Move some common logic to buffer class
|
5 年前 |
|
Ervin Teng
|
f2b3cd7f
|
Remove dead code
|
5 年前 |
|
Ervin Teng
|
28eba789
|
Migrate SAC
|
5 年前 |
|
Ervin Teng
|
2f82a550
|
Remove epsilon
|
5 年前 |
|
Ervin Teng
|
88b1123a
|
Merge branch 'master' of github.com:Unity-Technologies/ml-agents into develop-agentprocessor
|
5 年前 |
|
Ervin Teng
|
76abf968
|
Add back max_step logic
|
5 年前 |
|
Ervin Teng
|
8b3b9e6c
|
Move trajectory and related functions to trajectory.py
|
5 年前 |
|
Ervin Teng
|
f94365a2
|
No longer using ProcessingBuffer for PPO
|
5 年前 |
|
Ervin Teng
|
e0e57188
|
Clean up some stuff
|
5 年前 |
|
Ervin Teng
|
9c5fdd31
|
Stats reporting is working
|
5 年前 |
|
Ervin Teng
|
a97ffb47
|
Attempt reward reporting
|
5 年前 |
|
Ervin Teng
|
c2b729a6
|
Fix memory leak
|
5 年前 |
