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

[Refactor] Refactor DQN #1085

Merged
merged 24 commits into from
Apr 25, 2023
Merged

[Refactor] Refactor DQN #1085

Changes from 1 commit
Commits
Show all changes
24 commits
Select commit Hold shift + click to select a range
89dd22d
init
vmoens Apr 13, 2023
3382c37
amend
vmoens Apr 14, 2023
615f2f2
amend
vmoens Apr 15, 2023
8b55815
amend
vmoens Apr 15, 2023
56aabf1
Merge branch 'main' into rnn_example
vmoens Apr 16, 2023
a645cdc
amend
vmoens Apr 20, 2023
ea52133
Merge branch 'main' into rnn_example
vmoens Apr 21, 2023
1959339
amend
vmoens Apr 21, 2023
4a8f391
amend
vmoens Apr 21, 2023
53516fd
amend
vmoens Apr 23, 2023
04e6004
amend
vmoens Apr 23, 2023
a86b9a5
device
vmoens Apr 23, 2023
09a63d2
amend
vmoens Apr 23, 2023
441dc7c
amend
vmoens Apr 24, 2023
fe369aa
amend
vmoens Apr 24, 2023
e546c92
traj_lens
vmoens Apr 24, 2023
2324ca5
amend
vmoens Apr 24, 2023
0720b8f
amend
vmoens Apr 24, 2023
194c11e
amend
vmoens Apr 24, 2023
9792db3
init
vmoens Apr 24, 2023
04d77b9
amend
vmoens Apr 24, 2023
1e3763b
Merge remote-tracking branch 'origin/main' into dqn_refactor
vmoens Apr 24, 2023
0961c70
amend
vmoens Apr 25, 2023
8294746
amend
vmoens Apr 25, 2023
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
amend
  • Loading branch information
@vmoens
vmoens committed Apr 24, 2023
commit 0720b8f22241a8466774996472fa669ce6f88226
6 changes: 3 additions & 3 deletions tutorials/sphinx-tutorials/dqn_with_rnn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,11 +139,11 @@
)
stoch_policy.step(data.numel())
updater.step()
with set_exploration_type(ExplorationType.MODE):
rollout = env.rollout(10000, stoch_policy)
traj_lens.append(rollout.get(("next", "step_count")).max().item())

if i % 50 == 0:
with set_exploration_type(ExplorationType.MODE):
rollout = env.rollout(10000, stoch_policy)
traj_lens.append(rollout.get(("next", "step_count")).max().item())
print(f"Executed {len(traj_lens)} trajectories with step counts {traj_lens}")

print(f"Executed {len(traj_lens)} trajectories with step counts {traj_lens}")