Arec
|
f9729b0a9d
|
making expert data save s, a, sp. making dataloader also load batches thisway. renaming state to ego_state. converting path_x and path_y to single path variable. making number of samples for ray an argument. adjusting metrics, policy, and other functions to be able to handle this
|
2021-08-04 09:45:36 -07:00 |
|
Arec
|
6e524cf4b5
|
adding options for regularization and relative state masking via interaction graphs during data processing and experiment running. found 0.002 regularization on actions gives up to 3m of deviation with no collisions. added shell script to run ray experiments overnight
|
2021-08-02 14:38:06 -07:00 |
|
Arec
|
e30d0ab1ba
|
removing outliers from expert tracks
|
2021-07-29 08:20:40 -07:00 |
|
Arec
|
fdbdc7f9f0
|
making data processing happen on front end, not on data loader. saving a ton of time
|
2021-07-29 02:53:20 -07:00 |
|
Arec
|
1ca9914bf9
|
fixing bugs in transform, expert demo processing, main train function, and behavior cloning class. need to get bc class parameters to return nonempty list
|
2021-07-21 09:44:20 -07:00 |
|
Arec
|
2e29f42d75
|
add flag to process all tracks of a particular location
|
2021-07-20 05:46:43 -07:00 |
|
Arec
|
6964cb0c6c
|
got processing of expert demonstrations functional
|
2021-07-19 08:53:01 -07:00 |
|
Arec
|
8acfbc7993
|
updating expert data to keep track of deviations and check for collisions
|
2021-07-19 07:10:28 -07:00 |
|
Arec
|
2373d924b7
|
adding expert data loader and saver. same issue as previous commit, unable to get through full simulation with backtracked accelerations
|
2021-07-16 08:33:40 -07:00 |
|