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
1 parent
1f6b51d
commit 2edfd6f
Showing
214 changed files
with
13,837 additions
and
14 deletions.
There are no files selected for viewing
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
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
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
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
151 changes: 151 additions & 0 deletions
151
experiments/mpsc/models/rl_models/cartpole/track/cpo/none/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 +1,151 @@ | ||
| algo: cpo | ||
| algo_config: | ||
| cost_d: 0.0 | ||
| cost_v_lr: 0.0002 | ||
| damping_coeff: 0.01 | ||
| discount_factor: 0.98 | ||
| eval_batch_size: 20 | ||
| eval_interval: 40 | ||
| eval_save_best: true | ||
| filter_train_actions: false | ||
| gae_coeff: 0.97 | ||
| hidden1: 64 | ||
| hidden2: 64 | ||
| line_decay: 0.8 | ||
| log_interval: 40 | ||
| max_kl: 0.001 | ||
| max_steps: 600 | ||
| num_checkpoints: 0 | ||
| num_conjugate: 10 | ||
| num_epochs: 4000 | ||
| penalize_sf_diff: '' | ||
| pretrained: ./models/rl_models/cartpole/track/cpo_pretrain/ | ||
| save_interval: 0 | ||
| tensorboard: false | ||
| training: true | ||
| use_safe_reset: '' | ||
| v_lr: 0.0002 | ||
| value_epochs: 100 | ||
| device: cpu | ||
| kv_overrides: | ||
| - task_config.init_state=None | ||
| - task_config.use_constraint_penalty=False | ||
| - 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= | ||
| - task_config.done_on_violation= | ||
| - algo_config.penalize_sf_diff= | ||
| - algo_config.pretrained=./models/rl_models/cartpole/track/cpo_pretrain/ | ||
| output_dir: ./models/rl_models/cartpole/track/cpo/none/ | ||
| overrides: | ||
| - ./config_overrides/cartpole/cpo_cartpole.yaml | ||
| - ./config_overrides/cartpole/cartpole_track.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: '' | ||
| 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: 1 | ||
| obs_wrap_angle: false | ||
| physics: pyb | ||
| pyb_freq: 750 | ||
| randomized_inertial_prop: false | ||
| randomized_init: true | ||
| rew_act_weight: 0.01 | ||
| rew_exponential: true | ||
| rew_state_weight: | ||
| - 1 | ||
| - 0.01 | ||
| - 0.01 | ||
| - 0.01 | ||
| seed: 42 | ||
| task: traj_tracking | ||
| task_info: | ||
| num_cycles: 2 | ||
| trajectory_plane: zx | ||
| trajectory_position_offset: | ||
| - 0 | ||
| - 0 | ||
| trajectory_scale: 1 | ||
| trajectory_type: circle | ||
| use_constraint_penalty: false | ||
| verbose: false | ||
| use_gpu: false |
101 changes: 101 additions & 0 deletions
101
experiments/mpsc/models/rl_models/cartpole/track/cpo/none/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 +1,101 @@ | ||
| step,loss/approx_kl | ||
| 24000,0.000646044674795121 | ||
| 48000,0.0009329614695161581 | ||
| 72000,0.0009019307908602059 | ||
| 96000,0.000923275772947818 | ||
| 120000,0.0006421623402275145 | ||
| 144000,0.0009480011067353189 | ||
| 168000,0.0009906108025461435 | ||
| 192000,0.0009425210300832987 | ||
| 216000,0.0007847913657315075 | ||
| 240000,0.0007791825337335467 | ||
| 264000,0.0006357821403071284 | ||
| 288000,0.0009230932919308543 | ||
| 312000,0.0009148690733127296 | ||
| 336000,0.00095141347264871 | ||
| 360000,0.0009468137286603451 | ||
| 384000,0.0009762663976289332 | ||
| 408000,0.0006588250398635864 | ||
| 432000,0.0008665641071274877 | ||
| 456000,0.0009641050128266215 | ||
| 480000,0.0009798684623092413 | ||
| 504000,0.0009732079925015569 | ||
| 528000,0.0008943272405304015 | ||
| 552000,0.000996783492155373 | ||
| 576000,0.0009692904422990978 | ||
| 600000,0.0009578225435689092 | ||
| 624000,0.0007605528808198869 | ||
| 648000,0.0009490989032201469 | ||
| 672000,0.0009489719523116946 | ||
| 696000,0.0006397227407433093 | ||
| 720000,0.0009450088837184012 | ||
| 744000,0.0009264686959795654 | ||
| 768000,0.0009609815897420049 | ||
| 792000,0.0008726727101020515 | ||
| 816000,0.0006440887809731066 | ||
| 840000,0.0009824566077440977 | ||
| 864000,0.000682516663800925 | ||
| 888000,0.0009829368209466338 | ||
| 912000,0.0009785661241039634 | ||
| 936000,0.0006422321312129498 | ||
| 960000,0.000898991129361093 | ||
| 984000,0.0009843767620623112 | ||
| 1008000,0.000996031565591693 | ||
| 1032000,0.0006816338864155114 | ||
| 1056000,0.0009720880188979208 | ||
| 1080000,0.000980019336566329 | ||
| 1104000,0.0009498042054474354 | ||
| 1128000,0.0009569736430421472 | ||
| 1152000,0.0006414385861717165 | ||
| 1176000,0.0009859133278951049 | ||
| 1200000,0.0009931768290698528 | ||
| 1224000,0.0006413291557691991 | ||
| 1248000,0.0009956620633602142 | ||
| 1272000,0.0009710220620036125 | ||
| 1296000,0.0006393995136022568 | ||
| 1320000,0.0006447192281484604 | ||
| 1344000,0.0009979369351640344 | ||
| 1368000,0.0006416537798941135 | ||
| 1392000,0.0009277204517275095 | ||
| 1416000,0.0006415481329895556 | ||
| 1440000,0.0009986857185140252 | ||
| 1464000,0.0006506131030619144 | ||
| 1488000,0.000991199049167335 | ||
| 1512000,0.0009983122581616044 | ||
| 1536000,0.0009881022851914167 | ||
| 1560000,0.0006458890275098383 | ||
| 1584000,0.0009984839707612991 | ||
| 1608000,0.000990700558759272 | ||
| 1632000,0.0006463747704401612 | ||
| 1656000,0.000990919885225594 | ||
| 1680000,0.0009260903461836278 | ||
| 1704000,0.0006455002003349364 | ||
| 1728000,0.0009070246014744043 | ||
| 1752000,0.0009915938135236502 | ||
| 1776000,0.0006418480770662427 | ||
| 1800000,0.0009987179655581713 | ||
| 1824000,0.0006425059982575476 | ||
| 1848000,0.0009951347019523382 | ||
| 1872000,0.0009485813789069653 | ||
| 1896000,0.0009963957127183676 | ||
| 1920000,0.0006988556706346571 | ||
| 1944000,0.0009509280789643526 | ||
| 1968000,0.0009975767461583018 | ||
| 1992000,0.000639914651401341 | ||
| 2016000,0.0009169498225674033 | ||
| 2040000,0.0009927612263709307 | ||
| 2064000,0.0006458031130023301 | ||
| 2088000,0.0009963979246094823 | ||
| 2112000,0.0009705353295430541 | ||
| 2136000,0.0006517128786072135 | ||
| 2160000,0.0009954829001799226 | ||
| 2184000,0.0009975056163966656 | ||
| 2208000,0.0006464573089033365 | ||
| 2232000,3.2211271732465177e-15 | ||
| 2256000,0.0006424142047762871 | ||
| 2280000,0.0006442568264901638 | ||
| 2304000,0.0009942648466676474 | ||
| 2328000,0.0009692921885289252 | ||
| 2352000,0.0009863196173682809 | ||
| 2376000,0.0009901811135932803 | ||
| 2400000,0.0009780626278370619 |
Oops, something went wrong.