CartPole-v1 | prabhasak Workspace – Weights & Biases

Skip to main content

Prabhasak's group workspace

Group: CartPole-v1

1-4

of 4

Tags

Notes

Author

State

Finished

Start time

September 24th, 2020 9:20:01 AM

Runtime

3h 49m 26s

Tracked hours

3h 49m 26s

Run path

prabhasak/masters-thesis/1sl5c3rx

OS

Windows-10-10.0.18362-SP0

Python version

3.7.9

Command

train.py --env CartPole-v1 --algo dqn --exp-id 1 -il -eval -best -tb -wandb --num-trajs 5

System Hardware

CPU count	12
GPU count	1
GPU type	GeForce GTX 1660 Ti

W&B CLI Version

0.10.2

Group

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 29 keys
- algo:
  "dqn"
- cg_damping:
  0.001
- cg_iters:
  10
- check_callback:
  false
- device:
  "gpu"
- entcoeff:
  0
- env:
  "CartPole-v1"
- env_kwargs:
  null
- eval_callback:
  true
- exp_id:
  1
- gamma:
  0.99
- hyperparams_IL:{} 0 keys
- hyperparams_RL:{} 0 keys
- lam:
  1
- max_kl:
  0.001
- num_trajs:
  5
- policy:
  "MlpPolicy"
- save_best_model:
  true
- seed:
  42
- tensorboard:
  true
- timesteps_IL:
  0
- timesteps_per_batch:
  512
- timesteps_RL:
  0
- train_IL:
  true
- train_RL:
  false
- verbose:
  0
- vf_iters:
  3
- vf_stepsize:
  0.0001
- wandb_log:
  true

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 26 keys
- ▶
  advantage.bins:[] 33 items
- ▶
  advantage.values:[] 32 items
- entloss:
  0
- entropy:
  0.2188551127910614
- episodes:
  2,465
- expert episode length (mean):
  500
- expert episode length (std):
  0
- expert score (mean):
  500
- expert score (std):
  0
- iterations:
  1,954
- learning rate:
  0.0001
- mean episode length:
  500
- mean true reward (IL):
  500
- meankl:
  0.0011127778561785815
- num traj:
  5
- optimgain:
  0.011462435126304626
- seed:
  42
- surrgain:
  0.011462435126304626
- test episode length (mean):
  495.17
- test episode length (std):
  48.05789321224974
- test score (mean):
  495.1700134277344
- test score (std):
  48.057891845703125
- time elapsed:
  13,664.650992631912
- time per step:
  0.02023680927231908
- total loss:
  0.24289276089984924
- total steps:
  1,000,448

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

run-1sl5c3rx-history:v0

Loading...