134 Commits

Author	SHA1	Message	Date
Arec Jamgochian	e37911eeff	removing gail-trpo since performance is about the same as gail, adding experiment evaluation script, updating metric averaging to work	2022-02-27 23:03:28 -08:00
ebuehrle	4443492d3e	Add tuning script for GAIL (TRPO)	2022-02-27 14:38:40 +01:00
ebuehrle	4b4fa7e09a	Add tuning script for GAIL (PPO)	2022-02-27 14:14:08 +01:00
ebuehrle	71e3c5f816	Parametrize discriminator architecture	2022-02-26 14:53:29 +01:00
ebuehrle	35e6fb299c	Use collision rate as main metric	2022-02-26 14:28:58 +01:00
ebuehrle	1e24612347	Merge branch 'main' of https://github.com/sisl/InteractionImitation	2022-02-26 14:06:22 +01:00
ebuehrle	6876cf9625	Track collision rate	2022-02-26 13:50:53 +01:00
ebuehrle	dc9cbf329b	Enable safe options on evaluation env	2022-02-26 12:24:25 +01:00
Arec Jamgochian	c28c6c05b7	added ogail script and splitting up feasability on next line to avoid calculating it unnecessarily (though it might be fine as is)	2022-02-25 18:39:33 -08:00
Arec Jamgochian	fa98601fa6	fixing issues with lazylinear sequential, setting off a big run	2022-02-25 17:48:56 -08:00
Arec Jamgochian	59083ebce3	making option list indexable to visualize in tensorboard. noticing run from last night had much better performance under more long options, unclear if due to choice or environment factors, like episodes lasting longer. making stoponcollision and seed parameters. fixing ability to see reward metrics under ray/tune/, problem was they were being returned as tensors, not floats	2022-02-25 16:36:14 -08:00
Arec Jamgochian	99aa50a08b	added support for different activations, number of hidden layers, options, running a big run over this	2022-02-25 00:00:04 -08:00
Arec Jamgochian	7feea74eb8	adding stablebaselines, adding safe loading for nonCuda cluster	2022-02-24 23:18:02 -08:00
ebuehrle	5a5d8a7aff	WIP: Support different plan lengths	2022-02-25 01:32:54 +01:00
ebuehrle	336cf02278	Parameterize hidden layer size of policy, add some candidates to grid search	2022-02-23 18:14:23 +01:00
ebuehrle	f037c119cc	Set up for ray tune	2022-02-23 16:55:13 +01:00
ebuehrle	91f88983b0	Add learning rate schedule to SHAIL-PPO	2022-02-23 14:22:02 +01:00
Arec	68b066ec53	adding success rate, total distance, and survive time	2022-02-22 00:48:35 -08:00
Arec	e7f4f6a871	wrapping all environments in timelimit to stop runs longer than 100s, since some others were erroring	2022-02-21 17:54:29 -08:00
Arec	e7f8385628	updating rwse to work at different times, updating correct testing environment from roundabout, removing the assertion that a collision implies done in the evaluator, using nanmean and nanstd in averaging	2022-02-21 15:55:16 -08:00
ebuehrle	a242edc5d3	Fix predict for reparameterized modules ... Better way would probably be to rewrite flat_grad and reparam	2022-02-21 13:29:53 +01:00
ebuehrle	2da0e05782	Implement rwse	2022-02-21 11:05:19 +01:00
Arec	8c4ff03208	adding average absolute delta v, and tracking positions and setting up architecture to implement rwse	2022-02-21 00:06:39 -08:00
Arec	d2932951f6	adding metric saving and averaging over seeds	2022-02-20 23:22:46 -08:00
ebuehrle	84351e77f2	Add SHAIL-PPO	2022-02-18 06:54:52 +01:00
ebuehrle	1624e1a349	Add SHAIL	2022-02-17 23:51:40 +01:00
ebuehrle	cd58ce2898	Remove old code	2022-02-17 22:43:41 +01:00
ebuehrle	5bd8b42d9f	Merge updated files	2022-02-17 22:41:55 +01:00
ebuehrle	b78f95bab5	More checkpoints, adjustments for collision check	2022-02-16 10:19:50 +01:00
ebuehrle	c6a4c10605	Integrate options env and policy	2022-02-15 18:36:53 +01:00
ebuehrle	072c0ff417	Copy files	2022-02-15 14:03:22 +01:00
Arec	3e6fce42ee	BUG FIXES: moving around when policy is loaded, adding BaseAlgorithm abstract classes, correcting metrics, normalizng actions if idm environment is a normalized action one, manually updating environment graph when using idm, implementing idm forward class	2022-02-05 21:48:56 -08:00
Arec	795e1c08b6	adding metric comparisons and updating (note: pre-debug) init	2022-02-04 15:51:17 -08:00
Arec	31912416f1	adding pbar to evaluator and making metric save optional, adding typing to baselines	2022-02-02 22:19:40 -08:00
Arec	3ce86b31f7	adding Prop controller and IDMRulePolicy	2022-02-02 15:43:23 -08:00
Arec	3991306da0	updating evaluation wrapper to only store relevant variables during execution	2022-01-31 16:28:13 -08:00
Arec	3b60c14319	removing old implementation for rollout_and_save, and helper functions that were necessary for it	2022-01-18 18:03:38 -08:00
Arec	427a9e4f1b	adding rollout and trajectory flattening utilities. including old implementation in this commit	2022-01-18 17:53:56 -08:00
Arec	2c1dc6ca33	committing changes to start testing framework, removing shuffling of data	2022-01-17 15:47:40 -08:00
Arec	d34fa5774d	adding functions to save joint expert states and actions for repeated use in metrics, adding option to flatten loaded trajectories, adding class to not shuffle trajectories when saving experts to make sure it lines up with the joint states. checked that it does	2021-11-29 14:09:57 -08:00
Arec	a07050a748	fixing rendering system and main script to align with new repo changes	2021-11-09 07:15:07 -08:00
Arec	5799d095d9	adding tools to render directly from a policy, updating data generator, adding scratch files	2021-11-09 06:28:42 -08:00
ebuehrle	4a69322ed0	Move eps to constructor	2021-11-05 10:32:07 +01:00
ebuehrle	2aaaad36f0	Fix rendering ... - support predict() - move discount to OptionsEnv - fix RenderOptions	2021-11-02 16:15:34 +01:00
ebuehrle	8dd42abbf3	use discriminator preprocessing	2021-10-29 14:31:10 +02:00
ebuehrle	e57da1338a	Check emergency braking in available actions	2021-10-29 11:10:42 +02:00
ebuehrle	999cb80e13	Merge branch 'vectorize-propagation2'	2021-10-29 11:07:14 +02:00
ebuehrle	5bdf85562b	Merge branch 'main' into dev	2021-10-29 10:54:21 +02:00
Johannes Fischer	673b565e11	Update scratch	2021-10-28 18:31:52 +02:00
Johannes Fischer	1a1f6d8836	Merge branch 'main' of github.com:sisl/InteractionImitation	2021-10-28 18:17:47 +02:00