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.
Trained each approach 5 times with 5 seeds
- Loading branch information
1 parent
f83df4b
commit e98b837
Showing
1,490 changed files
with
29,377 additions
and
62 deletions.
There are no files selected for viewing
245 changes: 245 additions & 0 deletions
245
experiments/crazyflie/models/rl_models/ppo/mpsf_0.1/seed_4077/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 +1,245 @@ | ||
| algo: ppo | ||
| algo_config: | ||
| activation: tanh | ||
| actor_lr: 0.001 | ||
| clip_obs: 10 | ||
| clip_param: 0.2 | ||
| clip_reward: 10 | ||
| critic_lr: 0.001 | ||
| deque_size: 10 | ||
| entropy_coef: 0.01 | ||
| eval_batch_size: 10 | ||
| eval_interval: 10000 | ||
| eval_save_best: true | ||
| filter_train_actions: true | ||
| gae_lambda: 0.95 | ||
| gamma: 0.99 | ||
| hidden_dim: 128 | ||
| log_interval: 10000 | ||
| max_env_steps: 250000 | ||
| max_grad_norm: 0.5 | ||
| mini_batch_size: 256 | ||
| norm_obs: false | ||
| norm_reward: false | ||
| num_checkpoints: 0 | ||
| num_workers: 1 | ||
| opt_epochs: 20 | ||
| penalize_sf_diff: true | ||
| rollout_batch_size: 1 | ||
| rollout_steps: 1000 | ||
| save_interval: 0 | ||
| seed: 4077 | ||
| sf_penalty: 0.1 | ||
| target_kl: 0.01 | ||
| tensorboard: false | ||
| training: true | ||
| use_clipped_value: false | ||
| use_gae: true | ||
| use_safe_reset: true | ||
| device: cpu | ||
| kv_overrides: | ||
| - sf_config.cost_function=one_step_cost | ||
| - algo_config.filter_train_actions=True | ||
| - algo_config.penalize_sf_diff=True | ||
| - algo_config.use_safe_reset=True | ||
| - algo_config.sf_penalty=0.1 | ||
| - task_config.use_constraint_penalty=False | ||
| - task_config.seed=4077 | ||
| - algo_config.seed=4077 | ||
| - sf_config.seed=4077 | ||
| output_dir: ./models/rl_models/ppo/mpsf_0.1/seed_4077 | ||
| overrides: | ||
| - ./config_overrides/crazyflie_track.yaml | ||
| - ./config_overrides/ppo_crazyflie.yaml | ||
| - ./config_overrides/nl_mpsc.yaml | ||
| restore: null | ||
| safety_filter: nl_mpsc | ||
| seed: null | ||
| sf_config: | ||
| cost_function: one_step_cost | ||
| decay_factor: 0.85 | ||
| horizon: 10 | ||
| integration_algo: rk4 | ||
| mpsc_cost_horizon: 5 | ||
| n_samples: 600 | ||
| prior_info: | ||
| prior_prop: null | ||
| prior_prop_rand_info: null | ||
| randomize_prior_prop: false | ||
| q_lin: | ||
| - 0.8 | ||
| - 1.85 | ||
| - 0.8 | ||
| - 1.85 | ||
| - 10 | ||
| - 10 | ||
| r_lin: | ||
| - 2 | ||
| seed: 4077 | ||
| use_acados: true | ||
| use_terminal_set: false | ||
| warmstart: true | ||
| tag: temp | ||
| task: quadrotor | ||
| task_config: | ||
| adversary_disturbance: null | ||
| adversary_disturbance_offset: 0.0 | ||
| adversary_disturbance_scale: 0.01 | ||
| camera_view: | ||
| - 5 | ||
| - -40 | ||
| - -40 | ||
| - 0.5 | ||
| - -1 | ||
| - 0.5 | ||
| constraint_penalty: -1 | ||
| constraints: | ||
| - active_dims: | ||
| - 0 | ||
| - 1 | ||
| - 2 | ||
| - 3 | ||
| - 6 | ||
| - 7 | ||
| constrained_variable: state | ||
| constraint_form: bounded_constraint | ||
| lower_bounds: | ||
| - -0.95 | ||
| - -2 | ||
| - -0.95 | ||
| - -2 | ||
| - -0.25 | ||
| - -0.25 | ||
| upper_bounds: | ||
| - 0.95 | ||
| - 2 | ||
| - 0.95 | ||
| - 2 | ||
| - 0.25 | ||
| - 0.25 | ||
| - constrained_variable: input | ||
| constraint_form: default_constraint | ||
| cost: quadratic | ||
| ctrl_freq: 500 | ||
| disturbances: null | ||
| done_on_out_of_bound: true | ||
| done_on_violation: false | ||
| episode_len_sec: 15 | ||
| gui: false | ||
| inertial_prop: | ||
| Ixx: 1.4e-05 | ||
| Iyy: 1.4e-05 | ||
| Izz: 2.17e-05 | ||
| M: 0.0345 | ||
| inertial_prop_randomization_info: | ||
| Ixx: | ||
| distrib: uniform | ||
| high: 1.0e-06 | ||
| low: -1.0e-06 | ||
| Iyy: | ||
| distrib: uniform | ||
| high: 1.0e-06 | ||
| low: -1.0e-06 | ||
| Izz: | ||
| distrib: uniform | ||
| high: 1.0e-06 | ||
| low: -1.0e-06 | ||
| M: | ||
| distrib: uniform | ||
| high: 0.0025 | ||
| low: -0.0025 | ||
| info_in_reset: true | ||
| init_state: | ||
| init_p: 0 | ||
| init_phi: 0 | ||
| init_psi: 0 | ||
| init_q: 0 | ||
| init_r: 0 | ||
| init_theta: 0 | ||
| init_x: 0 | ||
| init_x_dot: 0 | ||
| init_y: 0 | ||
| init_y_dot: 0 | ||
| init_z: 1 | ||
| init_z_dot: 0 | ||
| init_state_randomization_info: | ||
| init_p: | ||
| distrib: uniform | ||
| high: 0.5 | ||
| low: -0.5 | ||
| init_phi: | ||
| distrib: uniform | ||
| high: 0.25 | ||
| low: -0.25 | ||
| init_psi: | ||
| distrib: uniform | ||
| high: 0 | ||
| low: 0 | ||
| init_q: | ||
| distrib: uniform | ||
| high: 0.5 | ||
| low: -0.5 | ||
| init_r: | ||
| distrib: uniform | ||
| high: 0 | ||
| low: 0 | ||
| init_theta: | ||
| distrib: uniform | ||
| high: 0.25 | ||
| low: -0.25 | ||
| init_x: | ||
| distrib: uniform | ||
| high: 0.95 | ||
| low: -0.95 | ||
| init_x_dot: | ||
| distrib: uniform | ||
| high: 2 | ||
| low: -2 | ||
| init_y: | ||
| distrib: uniform | ||
| high: 0.95 | ||
| low: -0.95 | ||
| init_y_dot: | ||
| distrib: uniform | ||
| high: 2 | ||
| low: -2 | ||
| init_z: | ||
| distrib: uniform | ||
| high: 1 | ||
| low: 1 | ||
| init_z_dot: | ||
| distrib: uniform | ||
| high: 0 | ||
| low: 0 | ||
| norm_act_scale: 0.1 | ||
| normalized_rl_action_space: false | ||
| obs_goal_horizon: 0 | ||
| physics: pyb | ||
| pyb_freq: 1000 | ||
| quad_type: 3 | ||
| randomized_inertial_prop: false | ||
| randomized_init: false | ||
| rew_act_weight: 0.0001 | ||
| rew_exponential: true | ||
| rew_state_weight: 1.0 | ||
| seed: 4077 | ||
| task: traj_tracking | ||
| task_info: | ||
| num_cycles: 1 | ||
| proj_normal: | ||
| - 0 | ||
| - 1 | ||
| - 1 | ||
| proj_point: | ||
| - 0 | ||
| - 0 | ||
| - 0.5 | ||
| trajectory_plane: xz | ||
| trajectory_position_offset: | ||
| - 0 | ||
| - 1 | ||
| trajectory_scale: 1 | ||
| trajectory_type: figure8 | ||
| use_constraint_penalty: false | ||
| verbose: false | ||
| use_gpu: false |
26 changes: 26 additions & 0 deletions
26
experiments/crazyflie/models/rl_models/ppo/mpsf_0.1/seed_4077/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 +1,26 @@ | ||
| step,loss/approx_kl | ||
| 10000,0.019042028230614957 | ||
| 20000,0.030633506896750373 | ||
| 30000,0.026581679276811578 | ||
| 40000,0.01583208901574835 | ||
| 50000,0.02909967950933302 | ||
| 60000,0.021294071866820256 | ||
| 70000,0.02641607148883244 | ||
| 80000,0.02318945480898644 | ||
| 90000,0.007602035258120544 | ||
| 100000,0.029347860710307334 | ||
| 110000,0.014340489992173387 | ||
| 120000,0.010300176194868983 | ||
| 130000,0.0070840485859662294 | ||
| 140000,0.029392864510494592 | ||
| 150000,0.03212166894615317 | ||
| 160000,0.016977267258334906 | ||
| 170000,0.03371633792412468 | ||
| 180000,0.01640852673444897 | ||
| 190000,0.03348114158725366 | ||
| 200000,0.047364376613404605 | ||
| 210000,0.033984803088242185 | ||
| 220000,0.028994489406856394 | ||
| 230000,0.04291667773892792 | ||
| 240000,0.022212137629200396 | ||
| 250000,0.024327125190757214 |
26 changes: 26 additions & 0 deletions
26
experiments/crazyflie/models/rl_models/ppo/mpsf_0.1/seed_4077/logs/loss/entropy_loss.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 +1,26 @@ | ||
| step,loss/entropy_loss | ||
| 10000,-1.8650468170642853 | ||
| 20000,-1.7552332321802773 | ||
| 30000,-1.68878675699234 | ||
| 40000,-1.6304927806059522 | ||
| 50000,-1.5138996839523315 | ||
| 60000,-1.3931940853595732 | ||
| 70000,-1.388410900036494 | ||
| 80000,-1.3235636234283448 | ||
| 90000,-1.2646600544452666 | ||
| 100000,-1.2286749998728435 | ||
| 110000,-1.1855341215928394 | ||
| 120000,-1.178399835030238 | ||
| 130000,-1.1548114120960236 | ||
| 140000,-1.0869037906328838 | ||
| 150000,-1.0821825047334035 | ||
| 160000,-1.0469228804111483 | ||
| 170000,-0.9771186093489328 | ||
| 180000,-0.9463309933741886 | ||
| 190000,-0.98116758565108 | ||
| 200000,-1.0034424304962157 | ||
| 210000,-0.965948274731636 | ||
| 220000,-0.9208977440992993 | ||
| 230000,-0.9026378452777862 | ||
| 240000,-0.876814016699791 | ||
| 250000,-0.7816491693258286 |
26 changes: 26 additions & 0 deletions
26
experiments/crazyflie/models/rl_models/ppo/mpsf_0.1/seed_4077/logs/loss/policy_loss.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 +1,26 @@ | ||
| step,loss/policy_loss | ||
| 10000,-0.005674048569055875 | ||
| 20000,-0.012599202696472678 | ||
| 30000,0.00027775632425281973 | ||
| 40000,-0.0019652279915649993 | ||
| 50000,-0.004312192235563267 | ||
| 60000,-0.011835860187362487 | ||
| 70000,-0.007146836617574167 | ||
| 80000,-0.0014260768091482836 | ||
| 90000,-0.005977628756711357 | ||
| 100000,-0.007523616881241553 | ||
| 110000,-0.005258733822307804 | ||
| 120000,-0.004637148353533257 | ||
| 130000,-0.011222052568600717 | ||
| 140000,-0.003314051613958418 | ||
| 150000,-0.002640003469618418 | ||
| 160000,-0.004508422728718014 | ||
| 170000,-0.004660241787124491 | ||
| 180000,-0.0031596650172195664 | ||
| 190000,0.0010233485010044754 | ||
| 200000,0.0015237208589164585 | ||
| 210000,0.007902507255455686 | ||
| 220000,0.0009553110313142845 | ||
| 230000,-0.009793386831435269 | ||
| 240000,-0.003094141107752506 | ||
| 250000,-0.0027178767337847796 |
26 changes: 26 additions & 0 deletions
26
experiments/crazyflie/models/rl_models/ppo/mpsf_0.1/seed_4077/logs/loss/value_loss.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 +1,26 @@ | ||
| step,loss/value_loss | ||
| 10000,5.2912078674909235 | ||
| 20000,4.862682331877378 | ||
| 30000,15.647721571981368 | ||
| 40000,9.19444863087563 | ||
| 50000,14.471390021750238 | ||
| 60000,5.1202633909702735 | ||
| 70000,6.919290430232465 | ||
| 80000,9.204161008723448 | ||
| 90000,11.34431719022297 | ||
| 100000,1.371981143216364 | ||
| 110000,4.36495685012213 | ||
| 120000,0.3911020827463573 | ||
| 130000,1.8652524237758008 | ||
| 140000,3.0497116766688506 | ||
| 150000,6.195875225190337 | ||
| 160000,2.9876203859621513 | ||
| 170000,0.6713922070680838 | ||
| 180000,2.134912566155845 | ||
| 190000,0.4016084477118814 | ||
| 200000,6.182694019625103 | ||
| 210000,0.4895621081164337 | ||
| 220000,0.5497357208378352 | ||
| 230000,2.353933525187545 | ||
| 240000,0.4196032263287692 | ||
| 250000,2.4522417304073882 |
26 changes: 26 additions & 0 deletions
26
...s/crazyflie/models/rl_models/ppo/mpsf_0.1/seed_4077/logs/stat/ep_constraint_violation.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 +1,26 @@ | ||
| step,stat/ep_constraint_violation | ||
| 10000,57.0 | ||
| 20000,41.0 | ||
| 30000,28.0 | ||
| 40000,21.0 | ||
| 50000,22.0 | ||
| 60000,12.0 | ||
| 70000,4.0 | ||
| 80000,20.0 | ||
| 90000,32.0 | ||
| 100000,7.0 | ||
| 110000,14.0 | ||
| 120000,5.5 | ||
| 130000,8.5 | ||
| 140000,7.5 | ||
| 150000,16.5 | ||
| 160000,17.0 | ||
| 170000,3.0 | ||
| 180000,9.5 | ||
| 190000,9.0 | ||
| 200000,17.5 | ||
| 210000,7.5 | ||
| 220000,8.0 | ||
| 230000,9.0 | ||
| 240000,8.0 | ||
| 250000,14.0 |
Oops, something went wrong.