rickstaa

Rickstaa's group workspace

Group: han2020_reproduction_small_horizon

1-20

of 60

Tags

extra

Notes

Author

rickstaa

State

Finished

Start time

March 10th, 2024 9:20:00 AM

Runtime

3h 10m 54s

Tracked hours

3h 10m 48s

Run path

rickstaa/stable-learning-control/endwggz4

Linux-6.5.0-21-generic-x86_64-with-glibc2.35

Python version

3.10.13

Git repository

git clone git@github.com:rickstaa/stable-learning-control.git

Git state

git checkout -b "han2020_reproduction_lac_cartpole_cost_alpha3_tune_exp_small_horizon_alp0-3_s78456" dd9b6c610b6fc24b1bd7fc9b7e75841d72a9a153

Command

/home/ricks/development/work/stable-learning-control/stable_learning_control/utils/run_entrypoint.py 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

System Hardware

CPU count	16
Logical CPU count	32
GPU count	1
GPU type	NVIDIA GeForce GTX 1070 Ti

W&B CLI Version

0.16.3

Group

han2020_reproduction_small_horizon

Job Type

train

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 40 keys
- ▶
  ac_kwargs:{} 3 keys
  - ▶
    activation:{} 2 keys
    - actor:
      "nn.ReLU"
    - critic:
      "nn.ReLU"
  - ▶
    hidden_sizes:{} 2 keys
    - ▶
      actor:[] 2 items
      - 0:
        256
      - 1:
        256
    - ▶
      critic:[] 3 items
      - 0:
        64
      - 1:
        64
      - 2:
        16
  - ▶
    output_activation:{} 1 key
    - actor:
      "nn.ReLU"
- adaptive_temperature:
  true
- alpha:
  2
- alpha3:
  0.3
- batch_size:
  256
- device:
  "gpu:1"
- env:
  "CartPoleCost-v1"
- env_class:
  "stable_gym.envs.classic_control.cartpole_cost.cartpole_cost.CartPoleCost"
- epochs:
  489
- exp_name:
  "han2020_reproduction_lac_cartpole_cost_alpha3_tune_exp_small_horizon_alp0-3"
- export:
  false
- gamma:
  0.99
- horizon_length:
  2
- labda:
  0.99
- lr_a:
  0.0001
- lr_a_decay_type:
  "linear"
- lr_a_final:
  0.0000000001
- lr_alpha:
  0.0001
- lr_alpha_decay_type:
  "linear"
- lr_alpha_final:
  0.0000000001
- lr_c:
  0.0003
- lr_c_decay_type:
  "linear"
- lr_c_final:
  0.0000000003
- lr_decay_ref:
  "step"
- lr_decay_type:
  "linear"
- lr_labda:
  0.0003
- lr_labda_decay_type:
  "constant"
- lr_labda_final:
  0.0000000003
- max_ep_len:
  250
- num_test_episodes:
  10
- opt_type:
  "minimize"
- polyak:
  0.995
- replay_size:
  1,000,000
- save_freq:
  10
- seed:
  78,456
- start_steps:
  0
- steps_per_epoch:
  2,048
- steps_per_update:
  80
- update_after:
  1,000
- update_every:
  100

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 32 keys
- AverageAlpha:
  0.008234198205173016
- AverageEntropy:
  -0.9687671065330504
- AverageEpLen:
  250
- AverageEpRet:
  25.204498291015625
- AverageErrorL:
  1.3802108764648438
- AverageLambda:
  1
- AverageLogPi:
  0.9687671065330504
- AverageLossAlpha:
  0.0002571780059952289
- AverageLossLambda:
  -123.25238037109376
- AverageLossPi:
  0.5732957720756531
- AverageLVals:
  2.23972749710083
- AverageTestEpLen:
  250
- AverageTestEpRet:
  35.94855880737305
- Epoch:
  489
- Lr_a:
  0.0000000001
- Lr_alpha:
  0.0000000001
- Lr_c:
  0.0000000003
- Lr_labda:
  0.0003
- MaxEpRet:
  39.086177825927734
- MaxLogPi:
  17.84563446044922
- MaxLVals:
  244.3435211181641
- MaxTestEpRet:
  85.0293960571289
- MinEpRet:
  15.015563011169434
- MinLogPi:
  -9.72785186767578
- MinLVals:
  0
- MinTestEpRet:
  7.522096633911133
- StdEpRet:
  8.790496826171875
- StdLogPi:
  1.3593944311141968
- StdLVals:
  11.675702095031738
- StdTestEpRet:
  23.61041259765625
- Time:
  11,445.366691589355
- TotalEnvInteracts:
  1,001,472

This run consumed these artifacts as inputs. Learn more

job

job-git_github.com_rickstaa_stable-learning-control.git_stable_learning_control_utils_run_entrypoint.py:v97

This run produced these artifacts as outputs. Total: 5. Learn more

run-endwggz4-history:v0