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.

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

Refactor Agent class #101

Merged
merged 63 commits into from
May 7, 2022
Merged
Changes from 1 commit
Commits
Show all changes
63 commits
Select commit Hold shift + click to select a range
9439f4d
init
vmoens Apr 28, 2022
51ec120
Merge remote-tracking branch 'origin/main' into agent_refactoring
vmoens Apr 28, 2022
08d698f
init
vmoens Apr 28, 2022
a39a990
lint
vmoens Apr 28, 2022
edd8879
minor
vmoens Apr 28, 2022
cc6afb2
minor
vmoens Apr 28, 2022
98f85c7
Merge branch 'main' into agent_refactoring
vmoens May 3, 2022
c5bef8e
amend
vmoens May 3, 2022
7dc507b
amend
vmoens May 3, 2022
3b4d488
amend
vmoens May 3, 2022
152b15c
amend
vmoens May 3, 2022
85165e8
lint
vmoens May 3, 2022
013442d
logging rewards
vmoens May 3, 2022
a53e37a
tests
vmoens May 3, 2022
5520ca1
lint
vmoens May 3, 2022
1cec671
fix mean error
vmoens May 3, 2022
ac332d5
refactoring agent to trainer
vmoens May 3, 2022
01450fa
lint
vmoens May 3, 2022
2e3a975
mp for dm_control from pixels
vmoens May 4, 2022
82cf428
mp for dm_control from pixels
vmoens May 4, 2022
8572755
mp for dm_control from pixels
vmoens May 4, 2022
35a9fb8
mp for dm_control from pixels
vmoens May 4, 2022
c77e5c9
mp for dm_control from pixels
vmoens May 4, 2022
8b25684
mp for dm_control from pixels
vmoens May 4, 2022
8e6a1d6
mp for dm_control from pixels
vmoens May 4, 2022
9759681
mp for dm_control from pixels
vmoens May 4, 2022
3c0176e
mp for dm_control from pixels
vmoens May 4, 2022
5038e7f
tensor to float/int/other item for log
vmoens May 4, 2022
f5a6cd5
tensor to float/int/other item for log
vmoens May 4, 2022
d1ddc2c
tensor to float/int/other item for log
vmoens May 4, 2022
fc9ba14
fix tests
vmoens May 4, 2022
db9244f
test recorder
vmoens May 4, 2022
4a23ac8
lint
vmoens May 4, 2022
9545817
fix device of reward norm
vmoens May 4, 2022
72942bd
cleanup postproc device
vmoens May 4, 2022
42c3522
cleanup postproc device
vmoens May 4, 2022
c056e59
cleanup postproc device
vmoens May 4, 2022
e3cd8b3
minor
vmoens May 4, 2022
f144d85
bf
vmoens May 4, 2022
31600d6
bf
vmoens May 5, 2022
3919a09
bf
vmoens May 5, 2022
f783d66
bf
vmoens May 5, 2022
106b601
bf
vmoens May 5, 2022
6affe3c
optim_steps_per_collection -> optim_steps_per_batch
vmoens May 5, 2022
b56695f
macos test fix
vmoens May 5, 2022
9dcf5bb
macos test fix
vmoens May 5, 2022
ce94dc5
macos test fix
vmoens May 5, 2022
fc9cec5
target_entropy for SAC
vmoens May 5, 2022
832ee2e
target_entropy for SAC
vmoens May 5, 2022
7697458
target_entropy for SAC
vmoens May 5, 2022
f724929
lint
vmoens May 5, 2022
4ef0caa
correct sac loss
vmoens May 5, 2022
98a6ca7
lint
vmoens May 5, 2022
6e247f1
update redq config
vmoens May 5, 2022
0eb227e
redq / sac fixes
vmoens May 6, 2022
585a61c
lint and minor
vmoens May 6, 2022
cd6e070
project action in gSDE contexts
vmoens May 6, 2022
daa77c6
hack: tanh for SAC + gSDE
vmoens May 6, 2022
32cf9ce
update configs
vmoens May 6, 2022
bde095a
agent to trainer in examples
vmoens May 6, 2022
4ad5862
cheetah commit
vmoens May 7, 2022
e7f0698
docs
vmoens May 7, 2022
539acb1
optimize imports
vmoens May 7, 2022
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
bf
  • Loading branch information
vmoens committed May 5, 2022
commit 106b601ca43bc27417e020d564ff62c89c26475a
2 changes: 1 addition & 1 deletion torchrl/trainers/trainers.py
Original file line number Diff line number Diff line change
Expand Up @@ -794,7 +794,7 @@ def __call__(self, batch: _TensorDict) -> Tuple[str, int]:
else:
current_frames = batch.numel() * self.frame_skip
self.frame_count += current_frames
return "collected_frames", self.frame_count
return "n_frames", self.frame_count


def _check_input_output_typehint(func: Callable, input: Type, output: Type):
Expand Down