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

Jump to bottom

Assembly first working state #3

Merged
merged 48 commits into from
Mar 19, 2024
Merged

Assembly first working state #3

merged 48 commits into from
Mar 19, 2024

Conversation

VictorColomb
Copy link
Collaborator

No description provided.

NicolasPllr1 and others added 30 commits March 12, 2024 10:22
@NicolasPllr1
first draft and impementations of MCTS
963c91f
@NicolasPllr1
selection and expension phase skeleton
9ffde52
@NicolasPllr1
better comments
4309b0b
@mdario-github
Added training module with loss computation and train/valid fcn
b6c85db
feat: simple dynamics, prediction and representation models
e3d06ec
@mdario-github
added dynamics model
e144dd1
feat: representation and prediction functions
4d3f9ff
@mdario-github
adapt for mask
cc31d9b
@JulienDelavande
mask action
fd2b53d
@JulienDelavande
Merge branch 'training' of https://github.com/SuReLI/muZero into trai…
a5fd2ab 
…ning
@mdario-github
added mask
3027c08
@NicolasPllr1
beggining of backup
140fa11
test: test notebook for models
a7f9e89
@Pianr
v3.3.2
e1470db
@mdario-github
add target_horizon parameter in train and valid functions
1a561e9
@ValentineBrgs
Modification Node + selection
a4b8cc8
@VictorColomb
Assembly: Replay buffer + tests
6c28aab
@Pianr
debuggage en cours
fe20a40
@Pianr
debuggage en cours
d1cc31e
@VictorColomb
Assembly: Training loop
cf8ee93
@Pianr
feat : working training module v1
efebd87
@Pianr
working validation_step()
3a4a241
@ValentineBrgs
full implementation V0
b2bf457
@accoumar12
Formatting
73b1d1d
@mdario-github
clean folder training
1d78829
@mdario-github
add optimizers
3e98149
@NicolasPllr1
started testing/debugging
7e9dbaa
fix: bug fixes on training step
d494431
@JulienDelavande
merge training
e0afb42
@JulienDelavande
add training to assembly
26b54ef
JulienDelavande and others added 18 commits March 12, 2024 19:59
@JulienDelavande
replace action by tensors -> working for training in assembly
65509e7
@JulienDelavande
delete models
07491d5
@NicolasPllr1
fix planning.py to pass the test script + debug option to print some …
4e5460d 
…logs
@NicolasPllr1
number of simulation as a test variable
bdee143
@NicolasPllr1
better comments + type of args
f64455f
@NicolasPllr1
move planning folder into a src/ folder
e9d7486
@NicolasPllr1
Merge pull request #2 from SuReLI/planning
4ff84a6 
Planning
@ValentineBrgs
Small modification of backup
edbcaa9
@VictorColomb
Formatting & python package
7da94df
@VictorColomb
Rename assembly to main and clean up
eb36bd9 
* Sort and clean up imports
* Move replay buffer into its directory
@VictorColomb
Fix replaybuffer circular import
d2ecb21
@guillaume117
debug verbose
7adc3e6
@Pianr
ajout du fichier acting à la branche assembly
4faa8b2
@Pianr
acting modified API to match main
3936acb
@Pianr
mask removed because not used yet
33a9fd1
@Pianr
n_simulation added to the API of acting
02f0492
@ValentineBrgs
Modification main and creation of __init__.py for acting
a4b015a
@ValentineBrgs
Merge branch 'assembly' of https://github.com/SuReLI/muZero into asse…
9f4d312 
…mbly
@VictorColomb VictorColomb merged commit 53b83d0 into main Mar 19, 2024
@VictorColomb VictorColomb deleted the assembly branch March 19, 2024 13:57
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
8 participants
@VictorColomb @NicolasPllr1 @mdario-github @JulienDelavande @Pianr @ValentineBrgs @accoumar12 @guillaume117