amrmousa-m

Amrmousa-m's group workspace

Group: HIM

1-3

of 3

Tags

Notes

HIM S96

Author

amrmousa-m

State

Finished

Start time

July 24th, 2025 6:05:52 PM

Runtime

16h 28m 6s

Tracked hours

16h 27m 58s

Run path

amrmousa-m/TAR_workspace/glbverbu

Linux-6.11.0-29-generic-x86_64-with-glibc2.39

Python version

3.10.18

Git repository

git clone https://github.com/ammousa/TARLoco.git

Git state

git checkout -b "HIM_S96_26" 1f357fe21aa877b3417c273a3adb0cd207804a57

Command

/home/amrmousa/0-WORK/TARLoco/standalone/tarloco/train.py --task go1-train-him-rough --max_iterations 20000 --headless --logger wandb --group HIM --device cuda:0 --note "HIM S96" --seed 96

System Hardware

CPU count	22
GPU count	1
GPU type	NVIDIA RTX 3500 Ada Generation Laptop GPU

W&B CLI Version

0.12.21

Group

HIM

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 3 keys
- ▶
  alg_cfg:{} 15 keys
- ▶
  policy_cfg:{} 7 keys
- ▶
  runner_cfg:{} 22 keys

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 31 keys
- Curriculum/terrain_levels:
  1.1927592754364014
- Episode_Reward/action_rate_l2:
  -0.1362324357032776
- Episode_Reward/ang_vel_xy_l2:
  -0.06707225739955902
- Episode_Reward/dof_acc_l2:
  -0.1471577286720276
- Episode_Reward/dof_pos_limits:
  0
- Episode_Reward/dof_torques_l2:
  -0.09387552738189696
- Episode_Reward/feet_air_time:
  -0.0007222710410133004
- Episode_Reward/flat_orientation_l2:
  0
- Episode_Reward/lin_vel_z_l2:
  -0.028768420219421387
- Episode_Reward/track_ang_vel_z_exp:
  0.34577903151512146
- Episode_Reward/track_lin_vel_xy_exp:
  0.7661226987838745
- Episode_Reward/undesired_contacts:
  -0.001969047589227557
- Episode_Termination/base_contact:
  3.5416667461395264
- Episode_Termination/time_out:
  2.5833334922790527
- log_dir:
  "2025-07-24_19-05-39"
- Loss/entropy_loss:
  -0.14659131318330765
- Loss/learning_rate:
  0.00011390625000000003
- Loss/mean_estimation_loss:
  0.009933556569740177
- Loss/mean_swap_loss:
  0.10194996409118176
- Loss/surrogate:
  -0.005920345691265538
- Loss/value_function:
  0.028530021104961632
- Metrics/base_velocity/error_vel_xy:
  0.34163808822631836
- Metrics/base_velocity/error_vel_yaw:
  0.3994831442832947
- Perf/collection time:
  2.5989904403686523
- Perf/learning_time:
  0.25546979904174805
- Perf/total_fps:
  34,438
- Policy/mean_noise_std:
  0.83195960521698
- Steps:
  19,998
- Train/mean_episode_length:
  643.16
- Train/mean_reward:
  12.476694787405432
- Train/reward_iter_score:
  8.065345764160156

This run produced these artifacts as outputs. Learn more

wandb-history

run-glbverbu-history:v0