Araffin's workspace
Runs
62
Name
11 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
algo
device
env
eval_episodes
eval_freq
gym_packages
hyperparams.learning_starts
log_folder
log_interval
n_eval_envs
n_jobs
n_startup_trials
n_timesteps
n_trials
no_optim_plots
num_threads
optimize_hyperparameters
pruner
sampler
save_freq
save_replay_buffer
saved_hyperparams.batch_size
saved_hyperparams.buffer_size
saved_hyperparams.callback
saved_hyperparams.ent_coef
saved_hyperparams.env_wrapper
saved_hyperparams.gamma
saved_hyperparams.gradient_steps
saved_hyperparams.learning_rate
saved_hyperparams.learning_starts
saved_hyperparams.n_timesteps
saved_hyperparams.normalize
saved_hyperparams.policy
saved_hyperparams.policy_kwargs
saved_hyperparams.sde_sample_freq
saved_hyperparams.tau
saved_hyperparams.train_freq
saved_hyperparams.use_sde
saved_hyperparams.use_sde_at_warmup
seed
tensorboard_log
track
trained_agent
truncate_last_trajectory
Finished
araffin
1h 22m 5s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto_0.1
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
2
0.00073
1000
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
dict(net_arch=[256, 256], dropout_rate=0.01, layer_norm=True)
-
0.02
1
-
-
5
/tmp/sb3
true
true
Finished
araffin
7m 34s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
500
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto_0.1
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
10
0.00073
500
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
dict(net_arch=[256, 256], dropout_rate=0.01, layer_norm=True)
-
0.02
1
-
-
321230364
/tmp/sb3
true
true
Finished
araffin
11m 16s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
500
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto_0.1
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
10
0.00073
500
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
dict(net_arch=[256, 256], dropout_rate=0.01, layer_norm=True)
-
0.02
1
-
-
294280503
/tmp/sb3
true
true
Finished
araffin
6m 44s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
0
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto_0.01
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
10
0.00073
0
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
dict(net_arch=[256, 256], dropout_rate=0.01, layer_norm=True)
-
0.02
1
-
-
2490288279
/tmp/sb3
true
true
Finished
araffin
8m 40s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
0
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto
[{"gym.wrappers.RescaleAction":{"min_action":-1,"max_action":1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
10
0.00073
0
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
dict(net_arch=[256, 256], dropout_rate=0.01, layer_norm=True)
-
0.02
1
-
-
2736329224
/tmp/sb3
true
true
Finished
araffin
15m 34s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
10
0.00073
1000
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
dict(net_arch=[256, 256], dropout_rate=0.01, layer_norm=True)
-
0.02
1
-
-
120584176
/tmp/sb3
true
true
Finished
araffin
16m 21s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
2
0.00073
1000
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
-
-
0.02
1
-
-
5
/tmp/sb3
true
true
Crashed
araffin
7s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
5
/tmp/sb3
true
true
Finished
araffin
2m 43s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
300000
[{"rl_zoo3.callbacks.ParallelTrainCallback":{"gradient_steps":16}},"rl_zoo3.callbacks.LapTimeCallback"]
auto
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
16
0.00073
1000
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
-
8
0.02
8
true
true
5
/tmp/sb3
true
true
Finished
araffin
15m 47s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
6
0.00073
1000
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
-
3
0.02
3
true
true
5
/tmp/sb3
true
true
Finished
araffin
30m 14s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
2
0.00073
1000
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
-
-
0.02
1
-
-
5
/tmp/sb3
true
true
Finished
araffin
14m 16s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto
[{"gym.wrappers.RescaleAction":{"min_action":-1,"max_action":1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
2
0.00073
1000
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
-
-
0.02
1
-
-
421581186
/tmp/sb3
true
true
Finished
araffin
4m 52s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
2
0.00073
1000
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
-
-
0.02
1
-
-
5
/tmp/sb3
true
true
Finished
araffin
31m 56s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
3
0.00073
1000
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
-
-
0.02
1
-
-
5
/tmp/sb3
true
true
Finished
araffin
32m 13s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
2
0.00073
1000
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
-
-
0.02
1
-
-
5
/tmp/sb3
true
true
Finished
araffin
1h 20m 50s
-
sac
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
10
0.00073
1000
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
dict(net_arch=[256, 256], dropout_rate=0.01, layer_norm=True)
-
0.02
1
-
-
2649124299
/tmp/sb3
true
true
Finished
araffin
2h 10m 16s
-
droq
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto
[{"gym.wrappers.RescaleAction":{"min_action":-1,"max_action":1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
10
-
1000
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
dict(net_arch=[256, 256], dropout_rate=0.01, layer_norm=True)
-
-
1
-
-
825975265
/tmp/sb3
true
true
Finished
araffin
23m 5s
-
droq
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
20
-
1000
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
dict(net_arch=[256, 256], dropout_rate=0.01, layer_norm=True)
-
-
1
-
-
779073638
/tmp/sb3
true
true
Finished
araffin
13m 51s
-
droq
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
20
-
1000
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
dict(net_arch=[256, 256], dropout_rate=0.01, layer_norm=True)
2
-
2
true
true
2510808023
/tmp/sb3
true
true
Finished
araffin
33m 33s
-
droq
auto
donkey-mountain-track-v0
5
-1
[]
-
logs
-1
1
1
10
2000000
500
false
-1
false
median
tpe
-1
false
256
-
["rl_zoo3.callbacks.LapTimeCallback"]
auto
[{"gym.wrappers.RescaleAction":{"max_action":1,"min_action":-1}},"ae.wrapper.AutoencoderWrapper",{"rl_zoo3.wrappers.HistoryWrapper":{"horizon":2}}]
0.995
10
-
1000
2000000
{'norm_obs': True, 'norm_reward': False}
MlpPolicy
dict(net_arch=[256, 256], dropout_rate=0.01, layer_norm=True)
2
-
2
true
true
486111705
/tmp/sb3
true
true
1-20
of 62