d0.1 | unirome_collab Overview – Weights & Biases

Skip to main content

Slimshadys's group workspace

Group: d0.1

1-2

of 2

Tags

Notes

Author

State

Finished

Start time

December 14th, 2023 10:25:16 AM

Runtime

3h 41m 17s

Tracked hours

3h 23m 28s

Run path

unirome_collab/SoftKick/zi4cmeih

OS

Windows-10-10.0.22631-SP0

Python version

3.9.18

Git repository

git clone https://github.com/SlimShadys/SoftKick

Git state

git checkout -b "trial-#1.1" fbffdb1187c6a008885d82a818d05a8666d049fd

Command

C:\Users\gianc\OneDrive\Desktop\rl\SoftKick\train_rlgym_ppo.py

System Hardware

CPU count	14
Logical CPU count	20
GPU count	1
GPU type	NVIDIA GeForce RTX 3060 Laptop GPU

W&B CLI Version

0.16.1

Group

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 14 keys
- ▶
  critic_layer_sizes:[] 4 items
  - 0:
    1,024
  - 1:
    512
  - 2:
    512
  - 3:
    512
- critic_lr:
  0.001
- exp_buffer_size:
  150,000
- gae_gamma:
  0.9908006132652292
- gae_lambda:
  0.95
- n_proc:
  40
- ▶
  policy_layer_sizes:[] 4 items
  - 0:
    1,024
  - 1:
    512
  - 2:
    512
  - 3:
    512
- policy_lr:
  0.001
- ppo_batch_size:
  50,000
- ppo_clip_range:
  0.2
- ppo_ent_coef:
  0.0001
- ppo_epochs:
  1
- ppo_minibatch_size:
  50,000
- ts_per_iteration:
  50,000

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 24 keys
- ball_height:
  92.99999237060548
- ball_speed:
  0
- boost_held:
  0.05161586403846741
- car_height:
  19.694080352783203
- car_speed:
  995.56005859375
- Collected Steps per Second:
  6,880.1871063196395
- Cumulative Model Updates:
  4,646
- Cumulative Timesteps:
  77,630,916
- demoed_rate:
  0
- Mean KL Divergence:
  0.00006015265535097569
- on_ground:
  0.5
- Overall Steps per Second:
  4,177.042332717314
- Policy Entropy:
  0.011429229440788427
- Policy Reward:
  16.345476247196274
- Policy Update Magnitude:
  0.004853709600865841
- PPO Batch Consumption Time:
  0.16201217969258627
- SB3 Clip Fraction:
  0.0006733333284500986
- Timestep Collection Time:
  7.270732500000122
- Timestep Consumption Time:
  4.705205500000375
- Timesteps Collected:
  50,024
- Total Iteration Time:
  11.975938000000497
- touch_rate:
  0
- Value Function Loss:
  0.04740355908870697
- Value Function Update Magnitude:
  0.06419694423675537

This run consumed these artifacts as inputs. Learn more

job-https___github.com_SlimShadys_SoftKick_train_rlgym_ppo.py:v6

Loading...

This run produced these artifacts as outputs. Total: 1. Learn more

run-zi4cmeih-history:v2

Loading...