New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Update mtsac_metaworld_mt50.py #1905
Conversation
@Mergifyio rebase |
Command
|
66ebacb
to
ef5426f
Compare
Codecov Report
@@ Coverage Diff @@
## master #1905 +/- ##
==========================================
+ Coverage 93.42% 93.47% +0.04%
==========================================
Files 192 192
Lines 10180 10180
Branches 1267 1267
==========================================
+ Hits 9511 9516 +5
+ Misses 441 437 -4
+ Partials 228 227 -1
Continue to review full report at Codecov.
|
679afd0
to
5b8df31
Compare
update the max_episode length of this example.
5b8df31
to
55c664d
Compare
@Mergifyio backport release-2020.06 |
Command
|
Backport #1905, #1975, #1908 to fix problems with max_eval_path_length being not used by mtsac and sac, and add checking for incorrect num_tasks being set in mtsac. Timelimit.truncated modified only when necessary This issue occurs when there are multiple garage envs that are nested or timelimit truncated = False is included in the environment keys. Previously, our timelimit truncated logic was written with the idea in mind that the key was only added when a time limit truncation occured. If an environment already has timelimit truncated = False in its keys then the previous behavior was to set Done = True which is the incorrect behavior. That was causing performance degradation in MTSAC and MTPPO/TRPO. Now Done is only true in the normal/trivial case, never if timelimit truncated is False.
Backport #1905, #1975, #1908 to fix problems with max_eval_path_length being not used by mtsac and sac, and add checking for incorrect num_tasks being set in mtsac. Timelimit.truncated modified only when necessary This issue occurs when there are multiple garage envs that are nested or timelimit truncated = False is included in the environment keys. Previously, our timelimit truncated logic was written with the idea in mind that the key was only added when a time limit truncation occured. If an environment already has timelimit truncated = False in its keys then the previous behavior was to set Done = True which is the incorrect behavior. That was causing performance degradation in MTSAC and MTPPO/TRPO. Now Done is only true in the normal/trivial case, never if timelimit truncated is False.
Backport #1905, #1975, #1908 to fix problems with max_eval_path_length being not used by mtsac and sac, and add checking for incorrect num_tasks being set in mtsac. Timelimit.truncated modified only when necessary This issue occurs when there are multiple garage envs that are nested or timelimit truncated = False is included in the environment keys. Previously, our timelimit truncated logic was written with the idea in mind that the key was only added when a time limit truncation occured. If an environment already has timelimit truncated = False in its keys then the previous behavior was to set Done = True which is the incorrect behavior. That was causing performance degradation in MTSAC and MTPPO/TRPO. Now Done is only true in the normal/trivial case, never if timelimit truncated is False.
Backport #1905, #1975, #1908 to fix problems with max_eval_path_length being not used by mtsac and sac, and add checking for incorrect num_tasks being set in mtsac. Timelimit.truncated modified only when necessary This issue occurs when there are multiple garage envs that are nested or timelimit truncated = False is included in the environment keys. Previously, our timelimit truncated logic was written with the idea in mind that the key was only added when a time limit truncation occured. If an environment already has timelimit truncated = False in its keys then the previous behavior was to set Done = True which is the incorrect behavior. That was causing performance degradation in MTSAC and MTPPO/TRPO. Now Done is only true in the normal/trivial case, never if timelimit truncated is False.
update the max_episode length of this example.