S-manolloff's workspace
Runs
22
State
Notes
User
Tags
Created
Runtime
Sweep
action
c.env_kwargs.auto_draw
c.env_kwargs.browser
c.env_kwargs.browser_mock
c.env_kwargs.driver
c.env_kwargs.failure_cost
c.env_kwargs.frames_per_step
c.env_kwargs.game_in_browser
c.env_kwargs.loglevel
c.env_kwargs.r_for_terminate
c.env_kwargs.reduced_action_set
c.env_kwargs.reload_on_reset
c.env_kwargs.render_mode
c.env_kwargs.stat_in_browser
c.env_kwargs.success_reward
c.env_kwargs.t_for_terminate
c.env_kwargs.text_in_browser
c.env_kwargs.time_cost_mult
c.learner_kwargs.batch_size
c.learner_kwargs.buffer_size
c.learner_kwargs.clip_range
c.learner_kwargs.ent_coef
c.learner_kwargs.exploration_final_eps
c.learner_kwargs.exploration_fraction
c.learner_kwargs.exploration_initial_eps
c.learner_kwargs.gae_lambda
c.learner_kwargs.gamma
c.learner_kwargs.gradient_steps
c.learner_kwargs.learning_starts
c.learner_kwargs.max_grad_norm
c.learner_kwargs.n_epochs
c.learner_kwargs.n_steps
c.learner_kwargs.normalize_advantage
c.learner_kwargs.policy
c.learner_kwargs.rms_prop_eps
c.learner_kwargs.sde_sample_freq
c.learner_kwargs.stats_window_size
c.learner_kwargs.target_update_interval
c.learner_kwargs.tau
c.learner_kwargs.train_freq
c.learner_kwargs.use_rms_prop
c.learner_kwargs.use_sde
c.learner_kwargs.vf_coef
c.learner_lr_schedule
Finished
-
s-manolloff
10h 48m 9s
train_rppo
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop-gym/vendor/chromedriver
10
4
false
WARN
-
false
false
browser
false
50
false
Do not close this window, training in progress...
10
32
-
0.2
0
-
-
-
0.95
0.99
-
-
0.5
10
1024
true
MlpLstmPolicy
-
4
-
-
-
-
-
false
0.5
const_0.0003
Finished
-
s-manolloff
10h 46m 20s
train_rppo
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop-gym/vendor/chromedriver
10
4
false
WARN
-
false
false
browser
false
50
false
Do not close this window, training in progress...
10
32
-
0.2
0
-
-
-
0.95
0.99
-
-
0.5
10
1024
true
MlpLstmPolicy
-
4
-
-
-
-
-
false
0.5
exp_decay_0.03_0.0002_0.5_10
Finished
-
s-manolloff
10h 52m 40s
train_rppo
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop-gym/vendor/chromedriver
10
4
false
WARN
-
false
false
browser
false
50
false
Do not close this window, training in progress...
10
32
-
0.2
0
-
-
-
0.95
0.99
-
-
0.5
10
256
true
MlpLstmPolicy
-
4
-
-
-
-
-
false
0.5
const_0.0003
Finished
-
s-manolloff
12h 52m 32s
train_rppo
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop-gym/vendor/chromedriver
10
4
false
WARN
-
false
false
browser
false
50
false
Do not close this window, training in progress...
10
32
-
0.2
0
-
-
-
0.95
0.99
-
-
0.5
10
256
true
MlpLstmPolicy
-
4
-
-
-
-
-
false
0.5
exp_decay_0.03_0.0002_0.5_10
Finished
-
s-manolloff
5h 38m 49s
train_a2c
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop-gym/vendor/chromedriver
10
4
false
WARN
-
false
false
browser
false
50
false
Do not close this window, training in progress...
10
-
-
-
0
-
-
-
1
0.99
-
-
0.5
-
50
false
MlpPolicy
0.00001
-1
100
-
-
-
true
false
0.5
exp_decay_0.05_0.0007_0.5_10
Finished
-
s-manolloff
5h 28m 12s
train_a2c
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop-gym/vendor/chromedriver
10
4
false
WARN
-
false
false
browser
false
50
false
Do not close this window, training in progress...
10
-
-
-
0
-
-
-
1
0.99
-
-
0.5
-
50
false
MlpPolicy
0.00001
-1
100
-
-
-
true
false
0.5
const_0.0007
Finished
-
s-manolloff
6h 8m 36s
train_a2c
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop-gym/vendor/chromedriver
10
4
false
WARN
-
false
false
browser
false
50
false
Do not close this window, training in progress...
10
-
-
-
0
-
-
-
1
0.99
-
-
0.5
-
5
false
MlpPolicy
0.00001
-1
100
-
-
-
true
false
0.5
exp_decay_0.05_0.0007_0.5_10
Finished
-
s-manolloff
6h 27m 33s
train_a2c
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop-gym/vendor/chromedriver
10
4
false
WARN
-
false
false
browser
false
50
false
Do not close this window, training in progress...
10
-
-
-
0
-
-
-
1
0.99
-
-
0.5
-
5
false
MlpPolicy
0.00001
-1
100
-
-
-
true
false
0.5
const_0.0007
Finished
-
s-manolloff
1d 13h 4m 36s
train_qrdqn
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop/vendor/chromedriver
10
4
false
WARN
-
true
false
browser
false
50
false
Do not close this window, training in progress...
10
64
100000
-
-
0
0.3
0.2
-
0.997
1
100000
-
-
-
-
MlpPolicy
-
-
-
512
1
4
-
-
-
const_0.001
Finished
-
s-manolloff
10h 36m 44s
train_qrdqn
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop/vendor/chromedriver
10
4
false
WARN
false
-
false
browser
false
50
-
Do not close this window, training in progress...
10
64
100000
-
-
0.001
0.5
0.2
-
0.995
1
100000
-
-
-
-
MlpPolicy
-
-
-
512
1
4
-
-
-
const_0.001
Finished
-
s-manolloff
5h 20m 20s
train_dqn
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop/vendor/chromedriver
10
1
false
WARN
false
-
false
browser
false
50
-
Do not close this window, training in progress...
10
64
100000
-
-
0.001
0.5
0.2
-
0.995
1
100000
-
-
-
-
MlpPolicy
-
-
-
512
1
4
-
-
-
const_0.001
Finished
-
s-manolloff
5h 35m 58s
train_dqn
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop/vendor/chromedriver
10
1
false
WARN
false
-
false
browser
false
50
-
Do not close this window, training in progress...
10
64
100000
-
-
0.001
0.5
0.2
-
0.995
1
100000
-
-
-
-
MlpPolicy
-
-
-
512
1
4
-
-
-
exp_decay_0.03_0.001_0.5_10
Finished
-
s-manolloff
5h 37m 55s
train_dqn
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop/vendor/chromedriver
10
1
false
WARN
false
-
false
browser
false
50
-
Do not close this window, training in progress...
5
64
100000
-
-
0.001
0.5
0.2
-
0.995
1
100000
-
-
-
-
MlpPolicy
-
-
-
512
1
4
-
-
-
const_0.001
Finished
-
s-manolloff
5h 36m 21s
train_dqn
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop/vendor/chromedriver
10
1
false
WARN
false
-
false
browser
false
50
-
Do not close this window, training in progress...
5
64
100000
-
-
0.001
0.5
0.2
-
0.995
1
100000
-
-
-
-
MlpPolicy
-
-
-
512
1
4
-
-
-
exp_decay_0.03_0.001_0.5_10
Finished
-
s-manolloff
4h 22m 55s
train_ppo
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop/vendor/chromedriver
10
4
false
WARN
false
-
false
browser
false
50
-
Do not close this window, training in progress...
10
32
-
0.4
0.0001
-
-
-
0.98
0.999
-
-
3
10
2048
true
MlpPolicy
-
4
-
-
-
-
-
false
0.5
const_0.0003
Finished
-
s-manolloff
4h 16m 56s
train_ppo
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop/vendor/chromedriver
10
4
false
WARN
false
-
false
browser
false
50
-
Do not close this window, training in progress...
10
32
-
0.4
0.0001
-
-
-
0.98
0.999
-
-
3
10
2048
true
MlpPolicy
-
4
-
-
-
-
-
false
0.5
step_0.03_0.0001_0.5_10
Finished
-
s-manolloff
4h 23m 49s
train_ppo
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop/vendor/chromedriver
10
4
false
WARN
false
-
false
browser
false
50
-
Do not close this window, training in progress...
10
32
-
0.4
0.0001
-
-
-
0.98
0.995
-
-
3
10
2048
true
MlpPolicy
-
4
-
-
-
-
-
false
0.5
const_0.0003
Finished
-
s-manolloff
4h 14m 3s
train_ppo
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop/vendor/chromedriver
10
4
false
WARN
false
-
false
browser
false
50
-
Do not close this window, training in progress...
10
32
-
0.4
0.0001
-
-
-
0.98
0.995
-
-
3
10
2048
true
MlpPolicy
-
4
-
-
-
-
-
false
0.5
step_0.03_0.0001_0.5_10
Finished
-
s-manolloff
8h 45m 7s
train_ppo
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop/vendor/chromedriver
10
4
false
WARN
false
-
false
browser
false
50
-
Do not close this window, training in progress...
10
32
-
0.4
0.0001
-
-
-
0.98
0.999
-
-
3
10
2048
true
MlpPolicy
-
4
-
-
-
-
-
false
0.5
const_0.0003
Finished
-
s-manolloff
8h 14m 47s
train_ppo
false
/Applications/Brave Browser.app/Contents/MacOS/Brave Browser
false
/Users/simo/Projects/qwop/vendor/chromedriver
10
4
false
WARN
false
-
false
browser
false
50
-
Do not close this window, training in progress...
10
32
-
0.4
0.0001
-
-
-
0.98
0.999
-
-
3
10
2048
true
MlpPolicy
-
4
-
-
-
-
-
false
0.5
step_0.03_0.0001_0.5_10
1-20
of 22