Skip to content

Add gymnasium support for DQN #370

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

Merged
vwxyzjn merged 19 commits into from
May 3, 2023
Merged

Add gymnasium support for DQN #370

Changes from 1 commit
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
90cd3f9
Add gymnasium dqn.py
Apr 1, 2023
0bc6b8f
Add gymnasium support for dqn_jax.py
Apr 1, 2023
2903faa
moved assert to parse func
Apr 6, 2023
089c14a
add gymnasium support for dqn atari
Apr 8, 2023
4b1f417
black formatting
Apr 8, 2023
599f9ad
fix make_env for rendering
Apr 9, 2023
b25647b
moved np to jnp
Apr 19, 2023
4ef9cd0
Merge branch 'master' into dqn-gymnasium
vwxyzjn Apr 25, 2023
60200d2
add warning mesage and update dependencies
vwxyzjn May 2, 2023
3d93220
update test cases
vwxyzjn May 2, 2023
27de676
update test cases
vwxyzjn May 2, 2023
c3b952e
pre-commit
vwxyzjn May 2, 2023
4d50ecf
bump shimmy version
vwxyzjn May 2, 2023
5d694bc
update shimmy
vwxyzjn May 2, 2023
717c98f
update shimmy
vwxyzjn May 2, 2023
c39ab46
trigger CI
vwxyzjn May 2, 2023
f342948
trigger CI
vwxyzjn May 2, 2023
9aea38d
trigger CI
vwxyzjn May 2, 2023
264d0e6
fix poetry
vwxyzjn May 2, 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
black formatting
  • Loading branch information
Valentin Canete committed Apr 8, 2023
commit 4b1f417550b954a794b039739b94654dfe89ad96
1 change: 0 additions & 1 deletion cleanrl/dqn_atari_jax.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -238,7 +238,6 @@ def mse_loss(params):
writer.add_scalar("charts/episodic_length", info["episode"]["l"], global_step)
writer.add_scalar("charts/epsilon", epsilon, global_step)


# TRY NOT TO MODIFY: save data to reply buffer; handle `final_observation`
real_next_obs = next_obs.copy()
for idx, d in enumerate(truncated):
Expand Down