forked from utiasDSL/safe-control-gym
-
Notifications
You must be signed in to change notification settings - Fork 4
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
pizarrob
committed
Aug 29, 2023
1 parent
5f4c5ce
commit c4d851a
Showing
1,919 changed files
with
385,242 additions
and
22 deletions.
There are no files selected for viewing
156 changes: 156 additions & 0 deletions
156
experiments/mpsc/models/rl_models/cartpole/stab/ppo/none_es_pen/config.yaml
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,156 @@ | ||
| algo: ppo | ||
| algo_config: | ||
| actor_lr: 0.0003 | ||
| clip_obs: 10.0 | ||
| clip_param: 0.2 | ||
| clip_reward: 10.0 | ||
| critic_lr: 0.001 | ||
| deque_size: 10 | ||
| entropy_coef: 0.01 | ||
| eval_batch_size: 10 | ||
| eval_interval: 1000 | ||
| eval_save_best: true | ||
| filter_train_actions: false | ||
| gae_lambda: 0.95 | ||
| gamma: 0.99 | ||
| hidden_dim: 64 | ||
| log_interval: 1000 | ||
| max_env_steps: 200000 | ||
| max_grad_norm: 0.5 | ||
| mini_batch_size: 64 | ||
| norm_obs: false | ||
| norm_reward: false | ||
| num_checkpoints: 0 | ||
| num_workers: 1 | ||
| opt_epochs: 10 | ||
| penalize_sf_diff: true | ||
| pretrained: ./models/rl_models/cartpole/stab/ppo_pretrain/ | ||
| rollout_batch_size: 1 | ||
| rollout_steps: 100 | ||
| save_interval: 10000 | ||
| sf_penalty: 300 | ||
| target_kl: 0.01 | ||
| tensorboard: false | ||
| training: true | ||
| use_clipped_value: false | ||
| use_gae: true | ||
| use_safe_reset: false | ||
| device: cpu | ||
| kv_overrides: | ||
| - task_config.init_state=None | ||
| - sf_config.cost_function=one_step_cost | ||
| - sf_config.mpsc_cost_horizon=2 | ||
| - sf_config.decay_factor=0.85 | ||
| - sf_config.soften_constraints=True | ||
| - algo_config.filter_train_actions=False | ||
| - algo_config.use_safe_reset=False | ||
| - task_config.done_on_violation=True | ||
| - algo_config.penalize_sf_diff=True | ||
| - algo_config.pretrained=./models/rl_models/cartpole/stab/ppo_pretrain/ | ||
| output_dir: ./models/rl_models/cartpole/stab/ppo/none_es_pen/ | ||
| overrides: | ||
| - ./config_overrides/cartpole/ppo_cartpole.yaml | ||
| - ./config_overrides/cartpole/cartpole_stab.yaml | ||
| - ./config_overrides/cartpole/nl_mpsc_cartpole_linear.yaml | ||
| restore: null | ||
| safety_filter: nl_mpsc | ||
| seed: 2 | ||
| sf_config: | ||
| cost_function: one_step_cost | ||
| decay_factor: 0.85 | ||
| horizon: 5 | ||
| integration_algo: LTI | ||
| mpsc_cost_horizon: 2 | ||
| n_samples: 6000 | ||
| prior_info: | ||
| prior_prop: null | ||
| prior_prop_rand_info: null | ||
| randomize_prior_prop: false | ||
| q_lin: | ||
| - 0.02 | ||
| - 0.001 | ||
| - 10 | ||
| - 0.5 | ||
| r_lin: | ||
| - 0.1 | ||
| slack_cost: 200 | ||
| soften_constraints: true | ||
| use_terminal_set: false | ||
| warmstart: true | ||
| tag: temp | ||
| task: cartpole | ||
| task_config: | ||
| adversary_disturbance: null | ||
| adversary_disturbance_offset: 0.0 | ||
| adversary_disturbance_scale: 0.01 | ||
| constraint_penalty: -1 | ||
| constraints: | ||
| - constrained_variable: state | ||
| constraint_form: default_constraint | ||
| lower_bounds: | ||
| - -2 | ||
| - -2 | ||
| - -0.16 | ||
| - -1 | ||
| upper_bounds: | ||
| - 2 | ||
| - 2 | ||
| - 0.16 | ||
| - 1 | ||
| - constrained_variable: input | ||
| constraint_form: default_constraint | ||
| cost: rl_reward | ||
| ctrl_freq: 15 | ||
| disturbances: null | ||
| done_on_out_of_bound: true | ||
| done_on_violation: true | ||
| episode_len_sec: 10 | ||
| gui: false | ||
| inertial_prop: | ||
| cart_mass: 1 | ||
| pole_length: 0.5 | ||
| pole_mass: 0.1 | ||
| inertial_prop_randomization_info: null | ||
| info_in_reset: true | ||
| init_state: null | ||
| init_state_randomization_info: | ||
| init_theta: | ||
| distrib: uniform | ||
| high: 0.16 | ||
| low: -0.16 | ||
| init_theta_dot: | ||
| distrib: uniform | ||
| high: 1 | ||
| low: -1 | ||
| init_x: | ||
| distrib: uniform | ||
| high: 2 | ||
| low: -2 | ||
| init_x_dot: | ||
| distrib: uniform | ||
| high: 2 | ||
| low: -2 | ||
| normalized_rl_action_space: true | ||
| obs_goal_horizon: 0 | ||
| obs_wrap_angle: false | ||
| physics: pyb | ||
| pyb_freq: 750 | ||
| randomized_inertial_prop: false | ||
| randomized_init: true | ||
| rew_act_weight: 0.1 | ||
| rew_exponential: true | ||
| rew_state_weight: | ||
| - 1 | ||
| - 1 | ||
| - 1 | ||
| - 1 | ||
| seed: 4077 | ||
| task: stabilization | ||
| task_info: | ||
| stabilization_goal: | ||
| - 0.7 | ||
| - 0 | ||
| stabilization_goal_tolerance: 0.0 | ||
| use_constraint_penalty: false | ||
| verbose: false | ||
| use_gpu: false |
201 changes: 201 additions & 0 deletions
201
experiments/mpsc/models/rl_models/cartpole/stab/ppo/none_es_pen/logs/loss/approx_kl.log
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,201 @@ | ||
| step,loss/approx_kl | ||
| 1000,0.008729896880686283 | ||
| 2000,0.000734184356406331 | ||
| 3000,0.00291068609803915 | ||
| 4000,-1.3645272701978684e-06 | ||
| 5000,0.006614508526399732 | ||
| 6000,0.01544560412876308 | ||
| 7000,0.0006366211455315351 | ||
| 8000,0.004890881758183241 | ||
| 9000,0.0023412187583744526 | ||
| 10000,0.005613256618380547 | ||
| 11000,0.007228300301358103 | ||
| 12000,-0.00400420562364161 | ||
| 13000,0.006578619172796607 | ||
| 14000,-0.0005445972084999085 | ||
| 15000,0.008278616517782212 | ||
| 16000,0.011816525785252451 | ||
| 17000,-0.0023400879930704833 | ||
| 18000,0.008586719632148743 | ||
| 19000,-0.0006781108677387238 | ||
| 20000,0.005032122880220413 | ||
| 21000,-0.005462524993345141 | ||
| 22000,0.002917123306542635 | ||
| 23000,-0.00032871197909116744 | ||
| 24000,0.0036752334795892238 | ||
| 25000,0.01376691684126854 | ||
| 26000,0.01612484287470579 | ||
| 27000,0.006670318730175495 | ||
| 28000,-0.0013380751013755798 | ||
| 29000,0.005172924604266882 | ||
| 30000,0.0046507432125508785 | ||
| 31000,0.010902715567499398 | ||
| 32000,0.016281079314649106 | ||
| 33000,0.013475347775965929 | ||
| 34000,0.002621723897755146 | ||
| 35000,0.01190365944057703 | ||
| 36000,0.0016663327813148498 | ||
| 37000,0.0003160743974149227 | ||
| 38000,0.001576053723692894 | ||
| 39000,0.004924441315233707 | ||
| 40000,0.0024348248727619646 | ||
| 41000,0.0017095220275223256 | ||
| 42000,-5.503920838236809e-05 | ||
| 43000,0.003813410922884941 | ||
| 44000,0.013407559320330619 | ||
| 45000,0.0015245947055518628 | ||
| 46000,0.02596539622172713 | ||
| 47000,-0.00210944339632988 | ||
| 48000,0.0023835944943130017 | ||
| 49000,0.02264212230220437 | ||
| 50000,0.02199324043467641 | ||
| 51000,0.004448459204286337 | ||
| 52000,0.009436118137091398 | ||
| 53000,-0.0010799305513501168 | ||
| 54000,0.00649948064237833 | ||
| 55000,-0.001802628394216299 | ||
| 56000,-0.02099919691681862 | ||
| 57000,0.0039390803314745424 | ||
| 58000,0.0007740736007690429 | ||
| 59000,0.00951544800773263 | ||
| 60000,0.004025054536759854 | ||
| 61000,0.01524742990732193 | ||
| 62000,0.009491441771388054 | ||
| 63000,0.012673575524240732 | ||
| 64000,0.0027870127931237222 | ||
| 65000,0.007525280769914389 | ||
| 66000,0.004612566251307726 | ||
| 67000,0.026369661558419466 | ||
| 68000,-0.0025882338173687457 | ||
| 69000,-0.01061791181564331 | ||
| 70000,0.015068107564002276 | ||
| 71000,0.00829745875671506 | ||
| 72000,0.012917507626116275 | ||
| 73000,-0.013731067907065153 | ||
| 74000,0.01958571085706353 | ||
| 75000,-0.0001483442261815071 | ||
| 76000,-0.0011200965382158756 | ||
| 77000,0.0008953817188739777 | ||
| 78000,0.0002586793154478073 | ||
| 79000,-0.008776371274143458 | ||
| 80000,0.014530325587838889 | ||
| 81000,0.01274836016818881 | ||
| 82000,0.007373989932239056 | ||
| 83000,0.012372850067913532 | ||
| 84000,0.002016447763890028 | ||
| 85000,0.020060299336910246 | ||
| 86000,0.020874370634555817 | ||
| 87000,0.008414185792207717 | ||
| 88000,0.01311216652393341 | ||
| 89000,0.009297892451286316 | ||
| 90000,0.005775431916117668 | ||
| 91000,0.020424895361065863 | ||
| 92000,0.005889152362942696 | ||
| 93000,0.0018017305061221122 | ||
| 94000,0.003054761327803135 | ||
| 95000,0.0019522182643413543 | ||
| 96000,0.0033927926793694495 | ||
| 97000,0.021219123527407645 | ||
| 98000,0.0018061263486742972 | ||
| 99000,0.01697399131953716 | ||
| 100000,0.013516435213387013 | ||
| 101000,0.00785445123910904 | ||
| 102000,-0.006084371916949749 | ||
| 103000,0.011851174943149089 | ||
| 104000,0.001215551793575287 | ||
| 105000,0.00013522040098905562 | ||
| 106000,-0.00922881830483675 | ||
| 107000,0.00014359671622514724 | ||
| 108000,0.001694943942129612 | ||
| 109000,0.0011710179969668388 | ||
| 110000,0.007342372089624405 | ||
| 111000,0.010471208393573761 | ||
| 112000,0.0034814819693565367 | ||
| 113000,0.026840898394584655 | ||
| 114000,0.020728708431124687 | ||
| 115000,0.005181179195642471 | ||
| 116000,0.03090306296944618 | ||
| 117000,0.028314807452261448 | ||
| 118000,0.011181743815541267 | ||
| 119000,0.00705907866358757 | ||
| 120000,0.014344541914761066 | ||
| 121000,0.029730680398643017 | ||
| 122000,0.004351761005818844 | ||
| 123000,-0.0003058729693293571 | ||
| 124000,0.03268703408539295 | ||
| 125000,0.01545734889805317 | ||
| 126000,-0.006995952501893043 | ||
| 127000,0.0071522252634167675 | ||
| 128000,0.004483654722571373 | ||
| 129000,0.011046481132507325 | ||
| 130000,0.004308021441102028 | ||
| 131000,-0.00540410652756691 | ||
| 132000,0.023018458113074302 | ||
| 133000,0.007347137667238712 | ||
| 134000,0.01149166990071535 | ||
| 135000,0.005793794244527817 | ||
| 136000,0.011545461602509022 | ||
| 137000,0.016494561359286307 | ||
| 138000,0.006517043337225914 | ||
| 139000,0.0030543511733412743 | ||
| 140000,0.011217675916850568 | ||
| 141000,0.010120180808007717 | ||
| 142000,0.0026907706633210182 | ||
| 143000,0.02641407437622547 | ||
| 144000,0.019319997914135457 | ||
| 145000,0.014785639569163322 | ||
| 146000,0.02574730645865202 | ||
| 147000,0.011972497962415219 | ||
| 148000,0.013819411769509316 | ||
| 149000,0.012093486823141575 | ||
| 150000,0.004326407425105571 | ||
| 151000,0.0291291618719697 | ||
| 152000,-0.004336457327008247 | ||
| 153000,0.013431697338819503 | ||
| 154000,0.001855066791176796 | ||
| 155000,0.014500624127686023 | ||
| 156000,0.007786365784704685 | ||
| 157000,0.007402325235307217 | ||
| 158000,0.030843445658683778 | ||
| 159000,0.00877070315182209 | ||
| 160000,-0.007646743021905422 | ||
| 161000,0.013534646108746528 | ||
| 162000,0.023433731868863106 | ||
| 163000,-0.007944797910749913 | ||
| 164000,0.024833100289106368 | ||
| 165000,0.011420492641627788 | ||
| 166000,0.010067783296108246 | ||
| 167000,0.017492294125258923 | ||
| 168000,0.012120826728641986 | ||
| 169000,-0.0002240002155303955 | ||
| 170000,0.021745909191668033 | ||
| 171000,0.008001739159226418 | ||
| 172000,0.016407574340701104 | ||
| 173000,0.03414605166763067 | ||
| 174000,-0.001893002912402153 | ||
| 175000,0.028219463862478734 | ||
| 176000,0.008424596674740315 | ||
| 177000,0.02602416221052408 | ||
| 178000,-0.0038695666939020158 | ||
| 179000,-0.007138722948729992 | ||
| 180000,0.00912117026746273 | ||
| 181000,-0.0017202425748109817 | ||
| 182000,0.05795675590634346 | ||
| 183000,0.01762190368026495 | ||
| 184000,0.0016452165320515633 | ||
| 185000,0.026887317188084126 | ||
| 186000,0.03456468842923641 | ||
| 187000,0.01526106745004654 | ||
| 188000,0.01378321908414364 | ||
| 189000,0.015503882616758346 | ||
| 190000,0.0011705541983246803 | ||
| 191000,0.05174665879458189 | ||
| 192000,0.02685304842889309 | ||
| 193000,0.010335128381848335 | ||
| 194000,0.008676587790250778 | ||
| 195000,0.0018693547695875167 | ||
| 196000,0.029819188080728053 | ||
| 197000,0.011678414605557918 | ||
| 198000,0.006377792358398438 | ||
| 199000,0.054620143957436085 | ||
| 200000,1.837722957134247e-05 |
Oops, something went wrong.