Vb/training render - #577
Open
Victorbares wants to merge 2 commits into
Open
Conversation
added 2 commits
August 27, 2026 10:47
Victorbares
marked this pull request as ready for review
August 27, 2026 12:36
vcharraut
requested changes
Aug 28, 2026
| init_mode: create_all_valid | ||
| # Enable computation of evaluation-only metrics | ||
| compute_eval_metrics: false | ||
| # Evaluate and render scenarios using the saved Gigaflow training distribution. |
Collaborator
There was a problem hiding this comment.
remove "saved Gigaflow"
Comment on lines
+145
to
+146
| unsigned char partner_blindness_active; | ||
| unsigned char phantom_braking_active; |
Collaborator
There was a problem hiding this comment.
can be derived from counter variable
Comment on lines
+490
to
+491
| agent->partner_blindness_active = 0; | ||
| agent->phantom_braking_active = 0; |
Collaborator
There was a problem hiding this comment.
can be derived from counter variable
| static void generate_traffic_light_states(Drive *env) { | ||
| int steps = env->scenario_length; | ||
| float dt = env->dt; | ||
| int use_training_behavior = !env->eval_mode || env->eval_training_render; |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
exact, randomized environment distribution from training (randomized agent counts, training vehicle
size ranges, and training traffic light logic) instead of static evaluation settings.
Why
benchmarks and the complex, noisy scenario distributions experienced during training.
whether an agent's sudden braking or collision was due to a policy error or an active perturbation.
Notes
--force.
max_agents_per_env.