Gocarx #18
Closed
Gocarx #18
Conversation
This file contains 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
Add the tricycle model of the gokart and a dummy agent demo to test the simulator
Add demo of two agent, reimplement the function of distance to boundary calculation
Add a new state yaw_rate, there might be still some compatibility problem
Test observe, metric and termination function. The dynamic model still need to be refined.
observe, reward , reset need to be further improved
neural network may return NaN after several iterations
evaluation visualized in wandb
the car can move forward
simplified some env structures and wrappers
- add acc_x and acc_y to trajectory array (needed by ignition)
add dynamics from forces solver and ignition
Move waymax to gocarx
* new metrics * minor * small updates * wip * unit tests * Update waymax/metrics/gokart_offroad.py Co-authored-by: code-review-doctor[bot] <72320148+code-review-doctor[bot]@users.noreply.github.com> * wip * final * revert back to GokartActionHistory * minor renaming * remove specific state metrics * minor * updates * minors * update bounds metric * Update gokart_offroad.py remove useless import * wip * to be verified, seems to work as expected * refactored metrics, rewards * Update waymax/rewards/linear_transformed_reward.py Co-authored-by: code-review-doctor[bot] <72320148+code-review-doctor[bot]@users.noreply.github.com> * fix tests * fixes --------- Co-authored-by: alezana <[email protected]> Co-authored-by: code-review-doctor[bot] <72320148+code-review-doctor[bot]@users.noreply.github.com>
Init/az refactoring
![code-review-doctor[bot]](https://avatars.githubusercontent.com/in/83430?s=60&v=4){kind=small}
| elif x.dtype == jnp.bool_: | ||
| return jnp.zeros_like(x).astype(jnp.bool_) | ||
| else: | ||
| raise ValueError("Unsupport dtype: %s" % x.dtype) |
There was a problem hiding this comment.
Suggested change
| raise ValueError("Unsupport dtype: %s" % x.dtype) | |
| raise ValueError(f"Unsupport dtype: {x.dtype}") |
f-string is easier to read, write, and less computationally expensive than legacy string formatting. More.
| passed into the environment. This runs metrics that may be specific to the | ||
| planning agent case. | ||
| def discount_spec(self) -> specs.BoundedArray: | ||
| return specs.BoundedArray(shape=tuple(), minimum=0.0, maximum=1.0, dtype=jnp.float32) |
There was a problem hiding this comment.
Suggested change
| return specs.BoundedArray(shape=tuple(), minimum=0.0, maximum=1.0, dtype=jnp.float32) | |
| return specs.BoundedArray(shape=(), minimum=0.0, maximum=1.0, dtype=jnp.float32) |
Using tuple literal syntax is simpler and computationally quicker. Read more.
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.