add a folder tracking our best models#430
Open
eugenevinitsky wants to merge 1 commit into
Open
Conversation
There was a problem hiding this comment.
Your free trial has ended. If you'd like to continue receiving code reviews, you can add a payment method here.
There was a problem hiding this comment.
Pull request overview
Adds a new models/4_19_26_rocket/ folder intended to track a “best model” configuration and a short description for reproducibility.
Changes:
- Added a model training/eval configuration YAML under
models/4_19_26_rocket/rocket-baseline-scaling/. - Added a brief text description documenting provenance/compatibility.
Reviewed changes
Copilot reviewed 2 out of 29 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| models/4_19_26_rocket/rocket-baseline-scaling/config.yaml | Adds a full training/eval config snapshot for the “rocket baseline scaling” model. |
| models/4_19_26_rocket/description.txt | Adds a one-line note about who trained the model and repo compatibility. |
Comments suppressed due to low confidence (2)
models/4_19_26_rocket/rocket-baseline-scaling/config.yaml:96
- These
wosac_*entries include; ...annotations and extra quoting, which YAML will treat as part of the value. As written, fields likewosac_control_mode/wosac_init_modewill not equal the expected enums (control_wosac,create_all_valid), and fields likewosac_aggregate_results/wosac_goal_radiuswon’t parse as bool/float. Replace the; ...notes with# ...YAML comments and remove the embedded quotes so the values parse to the intended types.
wosac_aggregate_results: True ; Only return aggregate results across all scenes
wosac_control_mode: '"control_wosac" ; Control the tracks to predict'
wosac_goal_radius: 2.0 ; Can shrink goal radius for WOSAC evaluation
wosac_init_mode: '"create_all_valid" ; Initialize from the tracks to predict'
wosac_init_steps: 10 ; When to start the simulation
models/4_19_26_rocket/rocket-baseline-scaling/config.yaml:98
wosac_num_agentsandwosac_num_rolloutsalso include; ...annotations; with YAML this makes them parse as strings rather than integers. If these are consumed programmatically (e.g., for sizing envs/rollouts), this will cause type errors or incorrect behavior. Use#for comments and keep the scalar values numeric.
wosac_num_agents: 256 ; Total number of WOSAC agents to evaluate
wosac_num_rollouts: 32 ; Number of policy rollouts per scene
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+83
to
+98
| human_replay_control_mode: '"control_sdc_only" ; Control only the self-driving car' | ||
| human_replay_eval: false | ||
| human_replay_num_agents: 64 ; This equals the number of scenarios, since we control | ||
| one agent in each | ||
| map_dir: pufferlib/resources/drive/binaries/eval | ||
| multi_scenario_eval: false | ||
| multi_scenario_num_scenarios: 250 | ||
| multi_scenario_simulation_mode: replay | ||
| num_agents: 512 | ||
| wosac_aggregate_results: True ; Only return aggregate results across all scenes | ||
| wosac_control_mode: '"control_wosac" ; Control the tracks to predict' | ||
| wosac_goal_radius: 2.0 ; Can shrink goal radius for WOSAC evaluation | ||
| wosac_init_mode: '"create_all_valid" ; Initialize from the tracks to predict' | ||
| wosac_init_steps: 10 ; When to start the simulation | ||
| wosac_num_agents: 256 ; Total number of WOSAC agents to evaluate | ||
| wosac_num_rollouts: 32 ; Number of policy rollouts per scene |
mpragnay
approved these changes
May 19, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.