Alex_ugr's workspace
Runs
18
Name
2 visualized
episode/episode_num: 1
episode/episode_num: 1
1
episode/episode_num: 3
episode/episode_num: 3
3
episode/episode_num: 50
episode/episode_num: 50
1
episode/episode_num: null
episode/episode_num: null
13
State
Notes
User
Tags
Created
Runtime
Sweep
algorithm
algorithm.log_interval
algorithm.name
algorithm.parameters.batch_size
algorithm.parameters.clip_range
algorithm.parameters.ent_coef
algorithm.parameters.gae_lambda
algorithm.parameters.gamma
algorithm.parameters.learning_rate
algorithm.parameters.max_grad_norm
algorithm.parameters.n_epochs
algorithm.parameters.n_steps
algorithm.parameters.policy
algorithm.parameters.verbose
algorithm.parameters.vf_coef
env_params.reward
environment
episodes
evaluation.eval_freq
evaluation.eval_length
id
python-version
seed
sinergym-version
wandb.artifact_name
wandb.artifact_type
wandb.dump_frequency
wandb.init_params.entity
wandb.init_params.project
wrappers.LoggerWrapper.flag
wrappers.LoggerWrapper.logger_class
env_params.config_params.timesteps_per_hour
algorithm.parameters._init_setup_model
algorithm.parameters.action_noise
algorithm.parameters.buffer_size
algorithm.parameters.device
algorithm.parameters.gradient_steps
algorithm.parameters.learning_starts
algorithm.parameters.optimize_memory_usage
algorithm.parameters.policy_delay
algorithm.parameters.sde_sample_freq
algorithm.parameters.stats_window_size
algorithm.parameters.target_entropy
algorithm.parameters.target_noise_clip
Killed
-
alex_ugr
9m 18s
-
-
1
SB3-SAC
256
-
auto
-
0.99
0.0003
-
-
-
MlpPolicy
0
-
LinearReward
Eplus-5zone-hot-continuous-stochastic-v1
5
2
1
SACExperimentExample
3.12.3 (main, Apr 10 2024, 05:33:47) [GCC 13.2.0]
3
3.3.7
experiment_SAC
training
500
alex_ugr
sinergym
true
sinergym.utils.logger.CSVLogger
-
true
-
1000000
auto
1
100
false
-
-1
100
auto
-
Finished
-
alex_ugr
2mo 18d 3h 44m 14s
-
SB3_PPO
1
SB3-SAC
256
-
auto
-
0.99
0.0003
-
-
-
MlpPolicy
0
-
LinearReward
["Eplus-5zone-hot-continuous-stochastic-v1","Eplus-5zone-mixed-continuous-stochastic-v1"]
4.33333
-
-
SACExperimentExample
3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]
3
["3.1.8","3.3.1"]
experiment_SAC
training
500
alex_ugr
sinergym
true
sinergym.utils.logger.CSVLogger
-
true
-
1000000
auto
1
100
false
-
-1
100
auto
-
Finished
-
alex_ugr
3h 39m 59s
-
-
1
SB3-SAC
256
-
auto
-
0.99
0.0003
-
-
-
MlpPolicy
0
-
ExpReward
Eplus-5zone-mixed-continuous-stochastic-v1
50
-
-
SACExperimentExample
3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]
3
3.2.0
experiment_SAC
training
500
alex_ugr
sinergym
true
sinergym.utils.logger.CSVLogger
-
true
-
1000000
auto
1
100
false
-
-1
100
auto
-
Failed
-
alex_ugr
1mo 9d 1h 46m 43s
-
-
1
["SB3-DDPG","SB3-PPO","SB3-SAC","SB3-TD3"]
113.84615
0.2
[0,"auto"]
0.95
0.99
0.00040769
0.5
10
2048
MlpPolicy
0.69231
0.5
["ExpReward","LinearReward","NormalizedLinearReward"]
["Eplus-5zone-hot-continuous-stochastic-v1","Eplus-5zone-mixed-continuous-stochastic-v1","Eplus-autobalance-mixed-discrete-stochastic-v1"]
18.30769
2
2
["DDPGExperimentExample","ExperimentExample","SACExperimentExample","TD3ExperimentExample","lineal_100_0"]
3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]
3
["3.1.4","3.1.7","3.1.8","3.2.0"]
["experiment1","experiment_DDPG","experiment_SAC","experiment_TD3"]
training
500
alex_ugr
sinergym
true
sinergym.utils.logger.CSVLogger
-
true
NormalActionNoise(mean=np.array([0]), sigma=np.array([0.1]))
1000000
auto
0.2
100
false
2
-1
100
auto
0.5
1-4
of 4