Skip to content
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.

Sign up for GitHub

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

Develop #266

Merged
merged 232 commits into from
Jul 6, 2021
Merged

Develop #266

Changes from 3 commits
Commits
Show all changes
232 commits
Select commit Hold shift + click to select a range
b88408b
feat: add turn-based pz tictactoe examples
ldfrancis Jun 4, 2021
ba7b82a
feat: Updates to use pz v 1.9.
KaleabTessera Jun 14, 2021
cfb2289
fix(mixing): Fix dims for qmix's q-values.
KaleabTessera Jun 14, 2021
a5fed95
fix(mixing): Fixed agent count for mixing with shared weights.
KaleabTessera Jun 14, 2021
4c0d45c
feature: add smac example runner.
sgrimbly Jun 14, 2021
9b8d2cf
feat(docker): sc2 docker file and instructions.
KaleabTessera Jun 14, 2021
78f9159
Merge branch 'develop' into feature/pz-upgrade-qmix-fix
KaleabTessera Jun 14, 2021
e9fa32c
fix: introduce agent_selection in mock environment
ldfrancis Jun 14, 2021
e8c457d
fix: modify pettingzoo sequential env wrapper
ldfrancis Jun 14, 2021
0ff38b8
fix: modify pz sequential env wrapper
ldfrancis Jun 14, 2021
753b499
Merge pull request #238 from instadeepai/feature/pz-upgrade-qmix-fix
KaleabTessera Jun 15, 2021
a6a49c2
fix: modify pz sequential env_wrapper
ldfrancis Jun 16, 2021
695de94
feat: make env loop wrappers behave like wrappers
ldfrancis Jun 16, 2021
0191757
fix: implement the select_action method of madqn
ldfrancis Jun 16, 2021
88d32aa
fix: modify sequential environment loop
ldfrancis Jun 16, 2021
2a02496
fix: adjust observation in pz sequential wrapper
ldfrancis Jun 16, 2021
bde5a41
fix: custom seq loop in tictactoe example
ldfrancis Jun 16, 2021
68fed3e
Merge branch 'develop' into feature/sequential-wrapper-and-loop
ldfrancis Jun 16, 2021
291d8fd
fix: Fix array2gif and smac imports
DriesSmit Jun 17, 2021
f6f0e15
fix: Fix wrappers init file.
DriesSmit Jun 17, 2021
777d136
Merge pull request #242 from instadeepai/fix/python-virtual-environme…
DriesSmit Jun 17, 2021
3e2deba
feat: include openspiel sequential wrapper
ldfrancis Jun 22, 2021
ed77ac9
feat: openspiel madqn tictactoe example
ldfrancis Jun 22, 2021
901a0d1
fix: ensure sequential loops collect all last obs
ldfrancis Jun 22, 2021
cda76d7
feat: include openspiel environment loop
ldfrancis Jun 22, 2021
8227824
fix: include num_agents property in pz wrapper
ldfrancis Jun 22, 2021
12b4daf
Updates to the readme
arnupretorius Jun 22, 2021
f3c356a
minor update to readme
arnupretorius Jun 22, 2021
efd48fb
feat: include a load util function for openspiel
ldfrancis Jun 22, 2021
6239449
fix: Include observation and action spaces
ldfrancis Jun 22, 2021
27ce14f
feat: include openspiel wrapper tests
ldfrancis Jun 22, 2021
8d74649
fix: set random player to None in example
ldfrancis Jun 22, 2021
20fe041
Merge branch 'develop' into feature/sequential-wrapper-and-loop
ldfrancis Jun 22, 2021
aed3d11
fix(build): include openspiel installation
ldfrancis Jun 22, 2021
e3e61bf
fix(ci): add -y to apt-get install
ldfrancis Jun 22, 2021
283c203
fix: Fix n-step reward calculation.
DriesSmit Jun 23, 2021
2ef421c
Provide implementation rubric
arnupretorius Jun 23, 2021
8bc90a9
Minor change
arnupretorius Jun 23, 2021
d1d148f
Update dockerfile to install mava pip package
arnupretorius Jun 23, 2021
0b645d4
update readme with roadmap and wish list
arnupretorius Jun 23, 2021
c92ef91
fix: Set tf prob version.
KaleabTessera Jun 23, 2021
391b89f
Minor updates to readme
arnupretorius Jun 23, 2021
0352ca1
Merge remote-tracking branch 'origin/bugfix/tf-probability' into fix-…
DriesSmit Jun 23, 2021
b05a07a
add bsuite link
arnupretorius Jun 23, 2021
09b9b14
Merge pull request #248 from instadeepai/bugfix/tf-probability
arnupretorius Jun 23, 2021
73c50fa
Merge branch 'develop' into fix-recurrent-maddpg
arnupretorius Jun 23, 2021
0715c70
fix: Remove comment.
DriesSmit Jun 23, 2021
ad63f8a
Merge branch 'develop' into feature/sequential-wrapper-and-loop
arnupretorius Jun 23, 2021
d901c72
Merge branch 'fix-recurrent-maddpg' of github.com:instadeepai/Mava in…
DriesSmit Jun 23, 2021
5c99232
Merge pull request #245 from instadeepai/fix-recurrent-maddpg
arnupretorius Jun 23, 2021
29c86a0
Update README.md
arnupretorius Jun 23, 2021
381a56a
update ot notice
arnupretorius Jun 23, 2021
ef95447
Merge branch 'develop' into update-readme
arnupretorius Jun 23, 2021
f58aed0
Remove poll
arnupretorius Jun 23, 2021
055bf26
Merge pull request #249 from instadeepai/update-readme
arnupretorius Jun 23, 2021
bbd5326
fix: Only update mixing network weights.
KaleabTessera Jun 18, 2021
9cf7ebb
feat: Network Stats wrapper for qmix.
KaleabTessera Jun 18, 2021
9bbc2f0
fix(qmix): Ensure to update correct target networks vars.
KaleabTessera Jun 24, 2021
0a04186
feat(networks): Default networks for maddpg, mad4pg, mappo and madqn.
KaleabTessera Jun 24, 2021
fe2e5c4
feat(networks): Add Gaussian noise exploration to maddpg and mad4pg.
KaleabTessera Jun 25, 2021
366dffa
fix: use a step_type method
ldfrancis Jun 25, 2021
c2f2e24
fix: remove random player
ldfrancis Jun 25, 2021
eddf68a
fix: remove duplicate action computation
ldfrancis Jun 25, 2021
bd27790
chore: remove placeholders in copyright
ldfrancis Jun 25, 2021
4439df2
Merge branch 'feature/sequential-wrapper-and-loop' of https://github.…
ldfrancis Jun 25, 2021
226be2e
Merge branch 'develop' into feature/sequential-wrapper-and-loop
ldfrancis Jun 25, 2021
8b5f651
fix: remove zero-sum validation statements
ldfrancis Jun 25, 2021
adc0e3f
fix: Only update mixing weights in grad update.
KaleabTessera Jun 25, 2021
60721f9
remove unused replay file.
arnupretorius Jun 28, 2021
7c9a1d5
update readme with mava animation gif
arnupretorius Jun 28, 2021
52b5e8f
Merge pull request #244 from instadeepai/feature/sequential-wrapper-a…
arnupretorius Jun 28, 2021
d0f587a
fix: Ensure mixing module wraps arch.
KaleabTessera Jun 28, 2021
0d24e7c
clean system builder class file
arnupretorius Jun 28, 2021
ac3ee86
Merge branch 'develop' into bugfix/qmix-training
KaleabTessera Jun 28, 2021
1589796
move abstract system class to tests for use in mock systems.
arnupretorius Jun 28, 2021
b5653e8
doc template for dial.
arnupretorius Jun 28, 2021
f4796e4
clean dial trainer.
arnupretorius Jun 28, 2021
61f3101
feat(arch): Default networks for qmix and vdn.
KaleabTessera Jun 28, 2021
ec110be
update dial readme
arnupretorius Jun 28, 2021
beefa98
docstring templates for mad4pg and updated readme
arnupretorius Jun 28, 2021
3185918
fix mypy issues
arnupretorius Jun 28, 2021
67b1121
doc templates for maddpg
arnupretorius Jun 28, 2021
62faf16
doc templates for madqn
arnupretorius Jun 28, 2021
32fb0c5
fix mypy issues.
arnupretorius Jun 28, 2021
a133cd4
fix(examples): Re-structured debug env examples.
KaleabTessera Jun 28, 2021
07af9da
update readme with gif animation
arnupretorius Jun 29, 2021
5b9fd0f
Longer animation gif
arnupretorius Jun 29, 2021
be8bbcd
Merge branch 'chore/cleanup' of https://github.com/instadeepai/Mava i…
arnupretorius Jun 29, 2021
ca1ccaa
Resize and reposition training gif
arnupretorius Jun 29, 2021
5205fe3
remove old images
arnupretorius Jun 29, 2021
1f48047
Test new gif
arnupretorius Jun 29, 2021
b638665
reduce gif size
arnupretorius Jun 29, 2021
6869de9
resolve merge conflict
arnupretorius Jun 29, 2021
16ad50e
feat: Added sc2 render and fixed seeding.
KaleabTessera Jun 29, 2021
1b1289c
fix: Use _n_agents from arch.
KaleabTessera Jun 29, 2021
a20d4e5
fix: ignored mypy issue.
KaleabTessera Jun 29, 2021
a877ecd
Merge pull request #250 from instadeepai/bugfix/qmix-training
arnupretorius Jun 30, 2021
5b1a08a
Merge branch 'develop' into feature/sc2-render-and-fix-seed
arnupretorius Jun 30, 2021
1ebb246
Merge pull request #255 from instadeepai/feature/sc2-render-and-fix-seed
arnupretorius Jun 30, 2021
fdceb3d
build: include open_spiel in dockerfile
ldfrancis Jun 30, 2021
f8ccb0f
update dial in readme
arnupretorius Jun 30, 2021
5eac67e
build: use local code as id-mava in installs
ldfrancis Jun 30, 2021
cfe0fc9
update dial system status
arnupretorius Jun 30, 2021
2de5b60
Merge pull request #256 from instadeepai/fix/easy-docker-openspiel-in…
DriesSmit Jun 30, 2021
912d375
fix(logging): Fixed EnvironmentLoopStatisticsBase to use correct _run…
KaleabTessera Jun 30, 2021
31b50f0
Merge branch 'develop' into bugfix/logging-running-stats
KaleabTessera Jun 30, 2021
518f455
resolve merge conflict
arnupretorius Jun 30, 2021
0c9086d
fix: Update dockerfile.
DriesSmit Jun 30, 2021
534c117
fix: Re-added method stubs.
KaleabTessera Jun 30, 2021
61811fe
Merge remote-tracking branch 'origin/bugfix/logging-running-stats' in…
KaleabTessera Jun 30, 2021
ae46dbb
update docstrings for dial
arnupretorius Jun 30, 2021
b2a71a9
minor change to dial system
arnupretorius Jun 30, 2021
7478a22
update dial builder docs
arnupretorius Jun 30, 2021
df766cd
minor update to dial builder
arnupretorius Jun 30, 2021
468b51f
Merge pull request #257 from instadeepai/bugfix/logging-running-stats
KaleabTessera Jun 30, 2021
70e4c0e
Merge remote-tracking branch 'origin/develop' into feature/redesign-e…
KaleabTessera Jun 30, 2021
69429a6
Merge branch 'develop' of https://github.com/instadeepai/Mava into ch…
arnupretorius Jun 30, 2021
e094f50
feat(networks): Added recurrent support for default archs.
KaleabTessera Jun 30, 2021
eb55cf7
fix(vdn): Consistent default value for shared weights.
KaleabTessera Jun 30, 2021
5972382
fix(examples): Fixed state based examples.
KaleabTessera Jun 30, 2021
44bcc88
feat(examples): Added recurrent examples using default networks.
KaleabTessera Jun 30, 2021
7799575
correction to dial doc strings.
arnupretorius Jul 1, 2021
f372717
cleaned doc strings for madqn
arnupretorius Jul 1, 2021
f46f09a
reposition training gif
arnupretorius Jul 1, 2021
1b6db01
Merge branch 'chore/cleanup' of https://github.com/instadeepai/Mava i…
arnupretorius Jul 1, 2021
6ab3702
feat(examples): Added default network and example for dial.
KaleabTessera Jul 1, 2021
b9b6cf0
doc string for qmix system.
arnupretorius Jul 1, 2021
8f83115
fix mypy issues
arnupretorius Jul 1, 2021
7d6c515
chore: Removed old examples.
KaleabTessera Jul 1, 2021
48a8503
doc strings for vdn
arnupretorius Jul 1, 2021
f82439d
fix mypy issues
arnupretorius Jul 1, 2021
dda3566
minor updates to missing string descriptions
arnupretorius Jul 1, 2021
3808a8b
maddpg doc strings
arnupretorius Jul 1, 2021
af990d4
doc strings for mad4pg
arnupretorius Jul 1, 2021
d0fd0d7
remove comments on internal imports
arnupretorius Jul 1, 2021
9c15cd0
remove unused system builder abstract class.
arnupretorius Jul 1, 2021
39f07be
update rubric for systems
arnupretorius Jul 1, 2021
4db7a79
almost done with mappo doc string updates
arnupretorius Jul 1, 2021
0725094
fix mypy issues
arnupretorius Jul 1, 2021
fa91cf5
chore: Cleaned up robocup env and example.
KaleabTessera Jul 1, 2021
56ae056
Merge branch 'chore/cleanup' of https://github.com/instadeepai/Mava i…
arnupretorius Jul 1, 2021
f090671
minor fix in maddpg.
arnupretorius Jul 1, 2021
1d39989
chore: Cleaned up debug env examples.
KaleabTessera Jul 1, 2021
5ad0948
chore: Updated flatland example.
KaleabTessera Jul 1, 2021
26f70a0
chore: Updated openspiel example.
KaleabTessera Jul 1, 2021
e93b672
chore: Update PZ examples.
KaleabTessera Jul 1, 2021
9accc43
chore: Updated smac examples.
KaleabTessera Jul 1, 2021
e4ae286
feat: Added coms network to default networks.
KaleabTessera Jul 1, 2021
7c4dd01
chore: Custom networked arch example.
KaleabTessera Jul 1, 2021
bba17e7
doc strings for mappo
arnupretorius Jul 2, 2021
97f796a
doc strings for generic system files
arnupretorius Jul 2, 2021
b1bddbf
add system images
arnupretorius Jul 2, 2021
4398391
enlarge qmix image
arnupretorius Jul 2, 2021
a46fe25
add architecture image
arnupretorius Jul 2, 2021
50b231b
add readme images.
arnupretorius Jul 2, 2021
964f2e5
Merge branch 'chore/cleanup' of https://github.com/instadeepai/Mava i…
arnupretorius Jul 2, 2021
a171ef5
add citations to readmes
arnupretorius Jul 2, 2021
87be82e
resize image in dial
arnupretorius Jul 2, 2021
1fb71df
Update readme for mad4pg system
arnupretorius Jul 2, 2021
f6a2a80
readme for maddpg
arnupretorius Jul 2, 2021
35a2977
new architecture image
arnupretorius Jul 2, 2021
9172707
resolve conflicts
arnupretorius Jul 2, 2021
8fc14eb
chore: Added switch dial example.
KaleabTessera Jul 2, 2021
f9984af
chore: Updated mpe examples.
KaleabTessera Jul 2, 2021
426678e
feat: Rewrote examples readme.
KaleabTessera Jul 2, 2021
1020ea1
chore: Added custom network example.
KaleabTessera Jul 2, 2021
97e70e6
smalle architecture image
arnupretorius Jul 2, 2021
aa99aa7
resolve merge conflict
arnupretorius Jul 2, 2021
0d28bc5
update madqn readme
arnupretorius Jul 2, 2021
80623cc
chore: Added references to readme and updated example orders.
KaleabTessera Jul 2, 2021
01b5366
Update mappo readme.
arnupretorius Jul 2, 2021
ebdbc96
update qmix readme
arnupretorius Jul 2, 2021
fb68c14
chore: Cleaned up examples readme.
KaleabTessera Jul 2, 2021
d3f35b4
update vdn readme
arnupretorius Jul 2, 2021
e236cee
Note on other training paradigms to be added soon
arnupretorius Jul 2, 2021
9bcc5c5
chore: Clean up wording in example readme.
KaleabTessera Jul 2, 2021
0a97abd
fix: Change the RoboCup example to use a recurrent network setup.
DriesSmit Jul 2, 2021
9eb5e62
fix: Removed pygame output whenever you mava.
KaleabTessera Jul 2, 2021
bcb0b6b
fix: Updated default example in makefile.
KaleabTessera Jul 2, 2021
32653bc
fix: Madqn recurrent example.
KaleabTessera Jul 2, 2021
737dcde
fix: Converted max grad norm to float.
KaleabTessera Jul 2, 2021
41372f1
chore: Set default num of executors in examples to 1.
KaleabTessera Jul 2, 2021
f8567ec
feat: Added scaling and custom loggers examples.
KaleabTessera Jul 2, 2021
1fc2c07
chore: Updated example's readme.
KaleabTessera Jul 2, 2021
ee6b34b
feat: Added quickstart notebook.
KaleabTessera Jul 2, 2021
b765b42
Merge pull request #259 from instadeepai/chore/cleanup
arnupretorius Jul 2, 2021
6f7491a
mypy changes to readmes
arnupretorius Jul 2, 2021
0baaa56
feat: Added docs strings for networks.
KaleabTessera Jul 2, 2021
c0b4cd0
Merge remote-tracking branch 'origin/develop' into feature/redesign-e…
KaleabTessera Jul 2, 2021
e8d1a14
chore: Auto format.
KaleabTessera Jul 2, 2021
c8fb764
chore: Temp removed using Network stats wrapper, this should be confi…
KaleabTessera Jul 2, 2021
ce707f4
Merge remote-tracking branch 'origin/feature/redesign-examples' into …
KaleabTessera Jul 2, 2021
765df4e
fix: Updated readme ref to examples.
KaleabTessera Jul 2, 2021
f0489c2
chore: Removed hyphen from all system names.
KaleabTessera Jul 5, 2021
79c626a
fix: Updated example links.
KaleabTessera Jul 5, 2021
39ac3b0
chore: Added quickstart notebook link to main readme.
KaleabTessera Jul 5, 2021
ea6c456
Merge pull request #260 from instadeepai/feature/redesign-examples
arnupretorius Jul 5, 2021
b0772d7
chore: Compressed gif and corrected links in readme.
KaleabTessera Jul 5, 2021
699e92b
fix: Updated license url.
KaleabTessera Jul 5, 2021
cd72fb6
chore: Updated gif size.
KaleabTessera Jul 5, 2021
32bfd85
basic cleanup of components
arnupretorius Jul 5, 2021
7994170
more cleanup, old todos
arnupretorius Jul 5, 2021
3c07340
fix mypy import issues
arnupretorius Jul 5, 2021
0273136
Merge branch 'develop' into feature/redesign-examples
arnupretorius Jul 5, 2021
243aecb
small change in adders
arnupretorius Jul 5, 2021
15c4059
Merge branch 'develop' into chore/component-cleanup
arnupretorius Jul 5, 2021
f2aee0d
basic clean of utils
arnupretorius Jul 5, 2021
48b0807
fix: Updated colab url.
KaleabTessera Jul 5, 2021
e7e75f3
Merge remote-tracking branch 'origin/feature/redesign-examples' into …
KaleabTessera Jul 5, 2021
65dde43
Merge pull request #262 from instadeepai/chore/component-cleanup
arnupretorius Jul 5, 2021
8c54d06
Merge branch 'develop' into chore/utils-cleanup
arnupretorius Jul 5, 2021
66b1eb2
chore: Added quickstart section to readme.
KaleabTessera Jul 5, 2021
65227d8
chore(readme): Updated readme, "mava usage" -> "usage".
KaleabTessera Jul 5, 2021
a22b173
Merge pull request #263 from instadeepai/chore/utils-cleanup
arnupretorius Jul 5, 2021
3c4a130
Merge branch 'develop' into feature/redesign-examples
arnupretorius Jul 6, 2021
800e07d
Update readme with arXiv paper link
arnupretorius Jul 6, 2021
6640097
quick wrappers cleanup
arnupretorius Jul 6, 2021
82dc76b
Merge pull request #265 from instadeepai/chore/wrapper-cleanup
arnupretorius Jul 6, 2021
f2f241c
Merge branch 'develop' into chore/update-readme
arnupretorius Jul 6, 2021
df6de58
Merge branch 'develop' into feature/redesign-examples
DriesSmit Jul 6, 2021
cb992cb
chore(readme): Added sc2 gif.
KaleabTessera Jul 6, 2021
3fa0889
Merge remote-tracking branch 'origin/feature/redesign-examples' into …
KaleabTessera Jul 6, 2021
6c3be09
chore: Changed gif layout in readme.
KaleabTessera Jul 6, 2021
5795309
chore: Centered gifs in readme.
KaleabTessera Jul 6, 2021
a50f315
Merge pull request #264 from instadeepai/chore/update-readme
arnupretorius Jul 6, 2021
e534fce
Merge branch 'develop' into feature/redesign-examples
KaleabTessera Jul 6, 2021
81d1ab9
chore(readme): Changed readme wording.
KaleabTessera Jul 6, 2021
e20a8d5
Merge remote-tracking branch 'origin/feature/redesign-examples' into …
KaleabTessera Jul 6, 2021
8c320c2
change the runner.
cwichka Jul 6, 2021
605edde
switch to ubuntu-latest - just for testing
cwichka Jul 6, 2021
b99f5bc
switching to onprem after updating the settings.
cwichka Jul 6, 2021
3110d18
Merge pull request #261 from instadeepai/feature/redesign-examples
KaleabTessera Jul 6, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view

These merge commits were added into this branch cleanly.

There are no new changes to show.