Simulate real world latency in eval.py #260
Closed
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Outdated suggestions cannot be applied.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 this does
DRAFT. Sketching out what we think "latency" means in the
rollout
function ofeval.py
. On this basis, we we will design the infrastructure/logic for handling latency. After we've validated it in sim, we will validate it in the real world. Rinse and repeat till we have it right.How it was tested
TBD
How to checkout & try? (for the reviewer)
Run:
python lerobot/scripts/eval.py -p lerobot/diffusion_pusht eval.n_episodes=1 eval.batch_size=1 env.episode_length=100 policy.n_action_steps=15 +do_simulate_latency=true
This change is