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

Assembly first working state #3

Merged
merged 48 commits into from
Mar 19, 2024
Merged

Assembly first working state #3

Changes from 1 commit
Commits
Show all changes
48 commits
Select commit Hold shift + click to select a range
963c91f
first draft and impementations of MCTS
NicolasPllr1 Mar 12, 2024
9ffde52
selection and expension phase skeleton
NicolasPllr1 Mar 12, 2024
4309b0b
better comments
NicolasPllr1 Mar 12, 2024
b6c85db
Added training module with loss computation and train/valid fcn
mdario-github Mar 12, 2024
e3d06ec
feat: simple dynamics, prediction and representation models
Mar 12, 2024
e144dd1
added dynamics model
mdario-github Mar 12, 2024
4d3f9ff
feat: representation and prediction functions
Mar 12, 2024
cc31d9b
adapt for mask
mdario-github Mar 12, 2024
fd2b53d
mask action
JulienDelavande Mar 12, 2024
a5fd2ab
Merge branch 'training' of https://github.com/SuReLI/muZero into trai…
JulienDelavande Mar 12, 2024
3027c08
added mask
mdario-github Mar 12, 2024
140fa11
beggining of backup
NicolasPllr1 Mar 12, 2024
a7f9e89
test: test notebook for models
Mar 12, 2024
e1470db
v3.3.2
Pianr Mar 12, 2024
1a561e9
add target_horizon parameter in train and valid functions
mdario-github Mar 12, 2024
a4b8cc8
Modification Node + selection
ValentineBrgs Mar 12, 2024
6c28aab
Assembly: Replay buffer + tests
VictorColomb Mar 12, 2024
fe20a40
debuggage en cours
Pianr Mar 12, 2024
d1cc31e
debuggage en cours
Pianr Mar 12, 2024
cf8ee93
Assembly: Training loop
VictorColomb Mar 12, 2024
efebd87
feat : working training module v1
Pianr Mar 12, 2024
3a4a241
working validation_step()
Pianr Mar 12, 2024
b2bf457
full implementation V0
ValentineBrgs Mar 12, 2024
73b1d1d
Formatting
accoumar12 Mar 12, 2024
1d78829
clean folder training
mdario-github Mar 12, 2024
3e98149
add optimizers
mdario-github Mar 12, 2024
7e9dbaa
started testing/debugging
NicolasPllr1 Mar 12, 2024
d494431
fix: bug fixes on training step
Mar 12, 2024
e0afb42
merge training
JulienDelavande Mar 12, 2024
26b54ef
add training to assembly
JulienDelavande Mar 12, 2024
65509e7
replace action by tensors -> working for training in assembly
JulienDelavande Mar 12, 2024
07491d5
delete models
JulienDelavande Mar 12, 2024
4e5460d
fix planning.py to pass the test script + debug option to print some …
NicolasPllr1 Mar 13, 2024
bdee143
number of simulation as a test variable
NicolasPllr1 Mar 13, 2024
f64455f
better comments + type of args
NicolasPllr1 Mar 13, 2024
e9d7486
move planning folder into a src/ folder
NicolasPllr1 Mar 13, 2024
4ff84a6
Merge pull request #2 from SuReLI/planning
NicolasPllr1 Mar 13, 2024
edbcaa9
Small modification of backup
ValentineBrgs Mar 14, 2024
7da94df
Formatting & python package
VictorColomb Mar 19, 2024
eb36bd9
Rename assembly to main and clean up
VictorColomb Mar 19, 2024
d2ecb21
Fix replaybuffer circular import
VictorColomb Mar 19, 2024
7adc3e6
debug verbose
guillaume117 Mar 19, 2024
4faa8b2
ajout du fichier acting à la branche assembly
Pianr Mar 19, 2024
3936acb
acting modified API to match main
Pianr Mar 19, 2024
33a9fd1
mask removed because not used yet
Pianr Mar 19, 2024
02f0492
n_simulation added to the API of acting
Pianr Mar 19, 2024
a4b015a
Modification main and creation of __init__.py for acting
ValentineBrgs Mar 19, 2024
9f4d312
Merge branch 'assembly' of https://github.com/SuReLI/muZero into asse…
ValentineBrgs Mar 19, 2024
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
Prev Previous commit
Next Next commit
mask removed because not used yet
  • Loading branch information
@Pianr
Pianr committed Mar 19, 2024
commit 33a9fd1deccb39b0b3c0fe1255d64508f6eebb96
1 change: 0 additions & 1 deletion src/acting/acting.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,6 @@ def acting(env, h, g, f, n_simulation=10):

o_prev = env.initial_state() # previous observation

mask = env.mask() #
is_terminal = False

while not is_terminal:
Expand Down