JumpMLP_Pos | BehaviorCloning Overview

Batu's group workspace

Group: JumpMLP_Pos

1-1

of 1

Tags

Notes

Author

batu

State

Finished

Start time

December 14th, 2021 3:01:50 PM

Runtime

1m 1s

Tracked hours

54s

Run path

batu/BehaviorCloning/1e30ok9b

Windows-10-10.0.19041-SP0

Python version

3.7.10

Git repository

git clone https://github.com/batu/RLAgency.git

Git state

git checkout -b "Baseline" 6e4e3bb5250b23f7cc217320753f7a5bca39a6ab

Command

<python with no main file> --ip=127.0.0.1 --stdin=9008 --control=9006 --hb=9005 --Session.signature_scheme="hmac-sha256" --Session.key=b"73d5dd21-7a2a-4508-9ae0-49b710cbfbee" --shell=9007 --transport="tcp" --iopub=9009 --f=C:\Users\batua\AppData\Local\Temp\tmp-8008qEaQXnfVXz4l.json

System Hardware

CPU count	16
GPU count	1
GPU type	NVIDIA GeForce RTX 3070 Laptop GPU

W&B CLI Version

0.12.6

Group

JumpMLP_Pos

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 15 keys
- activation:
  "torch.nn.functional.relu"
- architecture:
  "BaselineNoGraph( (dropout): Dropout(p=0, inplace=False) (layers): ModuleList( (0): Linear(in_features=6, out_features=512, bias=True) (1): Linear(in_features=512, out_features=512, bias=True) (2): Linear(in_features=512, out_features=3, bias=True) ) (input_layer): Linear(in_features=6, out_features=512, bias=True) (hidden_layers): ModuleList( (0): Linear(in_features=512, out_features=512, bias=True) ) (output_layer): Linear(in_features=512, out_features=3, bias=True) )"
- batch_size:
  512
- dropout_percentage:
  0
- env_name:
  "Jump"
- h_feats:
  512
- input_dim:
  6
- l2_regularization:
  0
- learning_rate:
  0.001
- loss:
  "torch.nn.functional.mse_loss"
- max_epochs:
  50
- num_layers:
  3
- observation:
  "pos"
- seed:
  4,752
- sweep:
  "SizeSweep"

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 17 keys
- epoch:
  42
- Mean of Gradients:
  0
- train_abs_error:
  0.4037728011608124
- train_loss_epoch:
  0.2822863757610321
- train_loss_step:
  0.2638368606567383
- trainer/global_step:
  1,891
- val_abs_error:
  0.3960292935371399
- val_loss_epoch:
  0.2772780954837799
- val_loss_step:
  0.2941156029701233
- val_mape_epoch:
  0.48608627915382385
- val_mape_jump_epoch:
  0.6899744272232056
- val_mape_jump_step:
  0.6892259120941162
- val_mape_step:
  0.4978252351284027
- val_mape_x_epoch:
  0.4366358518600464
- val_mape_x_step:
  0.4268365502357483
- val_mape_z_epoch:
  0.331648588180542
- val_mape_z_step:
  0.3774132132530213

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

wandb-history

run-1e30ok9b-history:v0