v0.5.1.3 | unirome_collab Overview – Weights & Biases

Skip to main content

Slimshadys's group workspace

Group: v0.5.1.3

1-3

of 3

Tags

Notes

Author

State

Finished

Start time

January 2nd, 2024 12:07:31 PM

Runtime

2h 46m 48s

Tracked hours

1h 5m 24s

Run path

unirome_collab/SoftKick/r4iytqa7

OS

Windows-10-10.0.22621-SP0

Python version

3.9.18

Git repository

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

Git state

git checkout -b "3rd-try" 9eefc5b6aa99f3e39d678836d1df2db2b7dbd3ab

Command

c:\Users\Gianmarco\Documents\Git\SoftKick\train_rlgym_ppo.py

System Hardware

CPU count	6
Logical CPU count	12
GPU count	1
GPU type	NVIDIA GeForce RTX 3060

W&B CLI Version

0.16.1

Group

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 19 keys
- ▶
  critic_layer_sizes:[] 4 items
  - 0:
    1,024
  - 1:
    512
  - 2:
    512
  - 3:
    512
- critic_lr:
  0.00025
- exp_buffer_size:
  150,000
- gae_gamma:
  0.9908006132652292
- gae_lambda:
  0.95
- min_inference_size:
  45
- n_proc:
  50
- ▶
  policy_layer_sizes:[] 4 items
  - 0:
    1,024
  - 1:
    512
  - 2:
    512
  - 3:
    512
- policy_lr:
  0.0003
- ppo_batch_size:
  50,000
- ppo_clip_range:
  0.2
- ppo_ent_coef:
  0.0001
- ppo_epochs:
  1
- ppo_minibatch_size:
  50,000
- shm_buffer_size:
  8,192
- standardize_obs:
  false
- standardize_returns:
  true
- timestep_limit:
  1,000,000,000
- ts_per_iteration:
  50,000

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 24 keys
- ball_height:
  157.02952575683594
- ball_speed:
  257.4258117675781
- boost_held:
  0.07527365535497665
- car_height:
  62.92689895629883
- car_speed:
  1,163.9405517578125
- Collected Steps per Second:
  11,217.671515046835
- Cumulative Model Updates:
  4,163
- Cumulative Timesteps:
  69,537,198
- demoed_rate:
  0.00164934026543051
- Mean KL Divergence:
  0.03107842616736889
- on_ground:
  0.15501798689365387
- Overall Steps per Second:
  8,426.390592819285
- Policy Entropy:
  0.05969892690579096
- Policy Reward:
  20.316215274884172
- Policy Update Magnitude:
  0.05580755323171616
- PPO Batch Consumption Time:
  0.12763595581054688
- SB3 Clip Fraction:
  0.04235999844968319
- Timestep Collection Time:
  4.45903589999989
- Timestep Consumption Time:
  1.4770763000001352
- Timesteps Collected:
  50,020
- Total Iteration Time:
  5.936112200000025
- touch_rate:
  0.030007997527718544
- Value Function Loss:
  2.2354657649993896
- Value Function Update Magnitude:
  0.0627463236451149

This run produced these artifacts as outputs. Learn more

run-r4iytqa7-history:v2

Loading...