JumpGraph_ConnectionBrokenTest | BehaviorCloning Workspace

Batu's group workspace

Group: JumpGraph_ConnectionBrokenTest

1-20

of 23

Tags

Notes

Author

batu

State

Finished

Start time

December 24th, 2021 8:52:49 AM

Runtime

9m 1s

Tracked hours

8m 58s

Run path

batu/BehaviorCloning/2vsncw26

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 "goal_connection_typerandom" 6e4e3bb5250b23f7cc217320753f7a5bca39a6ab

Command

<python with no main file> --ip=127.0.0.1 --stdin=9003 --control=9001 --hb=9000 --Session.signature_scheme="hmac-sha256" --Session.key=b"5944154f-cfa9-49f9-b83d-b1534b4ddd98" --shell=9002 --transport="tcp" --iopub=9004 --f=C:\Users\batua\AppData\Local\Temp\tmp-6616WyHzBvyXP1eG.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

JumpGraph_ConnectionBrokenTest

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 25 keys
- activation:
  "torch.nn.functional.relu"
- activation_first_layer:
  false
- add_node_id:
  false
- aggregation_method:
  "node"
- batch_size:
  128
- dropout:
  true
- edge_type:
  "goal_to_agent"
- env_name:
  "Jump"
- goal_connection_type:
  "random"
- hidden_dim:
  128
- id_one_hot:
  true
- input_dim:
  23
- learning_rate:
  0.005
- linear_input:
  true
- linear_output:
  true
- max_epochs:
  30
- model_type:
  "__main__.GCNLayer"
- ▶
  node_observation_specification:[] 1 item
  - 0:
    "abs_pos"
- num_layers:
  3
- obs:
  "pos"
- ▶
  observation_specification:{} 3 keys
  - ▶
    agent_pos:{} 3 keys
    - slice_start:
      13
    - slice_step:
      null
    - slice_stop:
      16
  - ▶
    goal_pos:{} 3 keys
    - slice_start:
      16
    - slice_step:
      null
    - slice_stop:
      19
  - ▶
    velocity:{} 3 keys
    - slice_start:
      9
    - slice_step:
      null
    - slice_stop:
      12
- residual:
  false
- self_loop:
  true
- sweep:
  "JumpGraphTest"
- typeID_one_hot:
  true

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 20 keys
- epoch:
  29
- ▶
  Fail Ending Position:{} 7 keys
- Mean of Gradients:
  0.00003021363409061451
- ▶
  Succes-Fail Starting Position:{} 7 keys
- Success Rate:
  0.004
- train_abs_error:
  0.6330387592315674
- train_loss_epoch:
  0.5400315523147583
- train_loss_step:
  0.5349486470222473
- trainer/global_step:
  5,279
- val_abs_error:
  0.6223217248916626
- val_loss_epoch:
  0.5218871831893921
- val_loss_step:
  0.668140172958374
- val_mape_epoch:
  0.6902132034301758
- val_mape_jump_epoch:
  0.5066397190093994
- val_mape_jump_step:
  0.7031911611557007
- val_mape_step:
  0.7931958436965942
- val_mape_x_epoch:
  0.8473712801933289
- val_mape_x_step:
  0.8382638096809387
- val_mape_z_epoch:
  0.7166284918785095
- val_mape_z_step:
  0.8381325006484985

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

wandb-history

run-2vsncw26-history:v0