rickstaa

Rickstaa's group workspace

Group: han2020_reproduction_sac_exp_bigger_initial_alpha

1-5

of 5

Tags

Notes

Author

rickstaa

State

Finished

Start time

March 15th, 2024 11:11:33 AM

Runtime

35m

Tracked hours

34m 54s

Run path

rickstaa/stable-learning-control/g2je3haq

Linux-6.5.0-17-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_sac_oscillator_complicated_alpha3_tune_exp_bigger_initial_alpha_s78456" e82e5374c65a0e3b674b8c0230973b759374af18

Command

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

System Hardware

CPU count	6
Logical CPU count	12
GPU count	2
GPU type	NVIDIA GeForce GTX 1070 Ti

W&B CLI Version

0.16.3

Group

han2020_reproduction_sac_exp_bigger_initial_alpha

Job Type

train

Config parameters are your model's inputs. Learn more

▶
Config parameters:{} 34 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:[] 2 items
      - 0:
        256
      - 1:
        256
  - ▶
    output_activation:{} 1 key
    - actor:
      "nn.ReLU"
- adaptive_temperature:
  true
- alpha:
  2
- batch_size:
  256
- device:
  "gpu:1"
- env:
  "OscillatorComplicated-v1"
- env_class:
  "stable_gym.envs.biological.oscillator_complicated.oscillator_complicated.OscillatorComplicated"
- epochs:
  98
- exp_name:
  "han2020_reproduction_sac_oscillator_complicated_alpha3_tune_exp_bigger_initial_alpha"
- export:
  false
- gamma:
  0.995
- lr_a:
  0.0001
- lr_a_decay_type:
  "linear"
- lr_a_final:
  0.000000001
- lr_alpha:
  0.0001
- lr_alpha_decay_type:
  "linear"
- lr_alpha_final:
  0.000000001
- lr_c:
  0.0003
- lr_c_decay_type:
  "linear"
- lr_c_final:
  0.000000003
- lr_decay_ref:
  "step"
- lr_decay_type:
  "linear"
- max_ep_len:
  400
- 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:
  50
- update_after:
  1,000
- update_every:
  100

Summary metrics are your model's outputs. Learn more

▶
Summary metrics:{} 33 keys
- AverageAlpha:
  1.0945110321044922
- AverageEntropy:
  -4.220136642456055
- AverageEpLen:
  400
- AverageEpRet:
  1,402.7010498046875
- AverageLogPi:
  4.220135688781738
- AverageLossAlpha:
  -0.24094043672084808
- AverageLossPi:
  340.9510192871094
- AverageLossQ:
  1,812.985107421875
- AverageQ1Vals:
  364.1753234863281
- AverageQ2Vals:
  364.4272155761719
- AverageTestEpLen:
  400
- AverageTestEpRet:
  1,537.724365234375
- Epoch:
  98
- Lr_a:
  0.000000001
- Lr_alpha:
  0.000000001
- Lr_c:
  0.000000003
- MaxEpRet:
  1,837.7694091796875
- MaxLogPi:
  26.435806274414062
- MaxQ1Vals:
  90,423.25
- MaxQ2Vals:
  90,428.703125
- MaxTestEpRet:
  1,613.3319091796875
- MinEpRet:
  1,232.9002685546875
- MinLogPi:
  -12.610136985778809
- MinQ1Vals:
  -818.6270751953125
- MinQ2Vals:
  -828.31298828125
- MinTestEpRet:
  1,448.5673828125
- StdEpRet:
  230.36798095703125
- StdLogPi:
  3.0336601734161377
- StdQ1Vals:
  4,251.498046875
- StdQ2Vals:
  4,251.35888671875
- StdTestEpRet:
  45.55302047729492
- Time:
  2,090.4031879901886
- TotalEnvInteracts:
  200,704

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:v113

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

run-g2je3haq-history:v0