Skip to content

Lab polish: CQL alpha-trajectory + Dreamer policy cleanup #19

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
ChatGPU merged 1 commit into from
May 27, 2026
Merged

Lab polish: CQL alpha-trajectory + Dreamer policy cleanup #19

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
Binary file added labs/rl_decision/lab_cql_offline_minigrid/assets/ablation_alpha_traj.png
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
162 changes: 122 additions & 40 deletions labs/rl_decision/lab_cql_offline_minigrid/notebook.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

4 changes: 2 additions & 2 deletions labs/world_models/lab_dreamer_cartpole_pixels/src/policy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,14 +60,14 @@ class PolicyConfig:

# Actor-critic
ac_hidden: int = 200
actor_lr: float = 1e-4
actor_lr: float = 3e-4
critic_lr: float = 3e-4
imagine_horizon: int = 12
imagine_batch: int = 32 # number of trajectories imagined per AC update
ac_updates_per_cycle: int = 50 # gradient steps on actor+critic each cycle
gamma: float = 0.99
lambda_: float = 0.95 # GAE/lambda-return mixing
actor_entropy: float = 0.005
actor_entropy: float = 0.05 # high entropy: WM dynamics are noisy enough that

# Init epsilon for the first cycle - actions are uniform random before any AC training.
initial_random_steps: int = 500
Expand Down
Loading