Hopper-v2 | prabhasak Workspace – Weights & Biases

Skip to main content

Prabhasak's group workspace

Group: Hopper-v2

1-8

of 8

Tags

Notes

Author

State

Finished

Start time

September 25th, 2020 5:02:00 AM

Runtime

4h 38m

Tracked hours

4h 38m

Run path

prabhasak/masters-thesis/7w68qv0o

OS

Windows-10-10.0.18362-SP0

Python version

3.7.9

Command

train.py --env Hopper-v2 --algo trpo --exp-id 1 -il -eval -best -tb -wandb --num-trajs 20

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:{} 30 keys
- algo:
  "trpo"
- cg_damping:
  0.1
- cg_iters:
  15
- check_callback:
  false
- device:
  "gpu"
- entcoeff:
  0.01
- env:
  "Hopper-v2"
- env_kwargs:
  null
- eval_callback:
  true
- exp_id:
  1
- gamma:
  0.99
- generate_expert:
  false
- hyperparams_IL:{} 0 keys
- hyperparams_RL:{} 0 keys
- lam:
  0.95
- max_kl:
  0.005
- num_trajs:
  20
- policy:
  "MlpPolicy"
- save_best_model:
  true
- seed:
  42
- tensorboard:
  true
- timesteps_IL:
  0
- timesteps_per_batch:
  2,048
- timesteps_RL:
  0
- train_IL:
  true
- train_RL:
  false
- verbose:
  0
- vf_iters:
  5
- vf_stepsize:
  0.001
- 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:
  0.0429607518017292
- entropy:
  4.296075344085693
- episodes:
  1,998
- expert episode length (mean):
  1,000
- expert episode length (std):
  0
- expert score (mean):
  3,543.8591918945312
- expert score (std):
  8.76113183672765
- iterations:
  489
- learning rate:
  0.001
- mean episode length:
  675.45
- mean true reward (IL):
  2,380.9888381749997
- meankl:
  0.004600389860570431
- num traj:
  20
- optimgain:
  0.06539865583181381
- seed:
  42
- surrgain:
  0.02243790216743946
- test episode length (mean):
  1,000
- test episode length (std):
  0
- test score (mean):
  3,597.791015625
- test score (std):
  2.8599202632904053
- time elapsed:
  16,330.566085577011
- time per step:
  0.026102915056981143
- total loss:
  4.431473043747246
- total steps:
  1,001,472

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

run-7w68qv0o-history:v0

Loading...