Amrmousa-m's group workspace
Group: Teacher
State
Notes
User
Tags
Created
Runtime
Sweep
Hostname
ID
alg_cfg.aux_loss_coef
alg_cfg.class_name
alg_cfg.clip_param
alg_cfg.desired_kl
alg_cfg.entropy_coef
alg_cfg.gamma
alg_cfg.lam
alg_cfg.lr_max
alg_cfg.lr_min
alg_cfg.max_grad_norm
alg_cfg.num_learning_epochs
alg_cfg.num_mini_batches
alg_cfg.optimizer
alg_cfg.schedule
alg_cfg.use_clipped_value_loss
alg_cfg.value_loss_coef
policy_cfg.activation
policy_cfg.actor_hidden_dims
policy_cfg.arch_type
policy_cfg.aux_loss_coef
policy_cfg.class_name
policy_cfg.clip_action
policy_cfg.critic_hidden_dims
policy_cfg.init_noise_std
policy_cfg.latent_dims
policy_cfg.mlp_encoder_dims
policy_cfg.num_hist
policy_cfg.num_hist_short
policy_cfg.rnn_hidden_dims
policy_cfg.rnn_out_features
policy_cfg.rnn_type
policy_cfg.squash_mode
policy_cfg.trans_hidden_dims
runner_cfg.algorithm.aux_loss_coef
runner_cfg.algorithm.class_name
runner_cfg.algorithm.clip_param
runner_cfg.algorithm.desired_kl
runner_cfg.algorithm.entropy_coef
runner_cfg.algorithm.gamma
runner_cfg.algorithm.lam
Finished
Teacher S96
amrmousa-m
1d 6h 48m 48s
-
-
fhfi1udm
-
PPO
0.2
0.01
0.01
0.99
0.95
0.001
0.00001
1
5
4
Adam
adaptive
true
1
elu
[512,256,128]
-
-
ActorCriticMlpDblEncExpert
100
[512,256,128]
1
20
[256,128,64]
1
-
-
-
-
clip
[256,128]
-
PPO
0.2
0.01
0.01
0.99
0.95
Finished
Teacher S41
amrmousa-m
19h
-
-
cucm79le
-
PPO
0.2
0.01
0.01
0.99
0.95
0.001
0.00001
1
5
4
Adam
adaptive
true
1
elu
[512,256,128]
-
-
ActorCriticMlpDblEncExpert
100
[512,256,128]
1
20
[256,128,64]
1
-
-
-
-
clip
[256,128]
-
PPO
0.2
0.01
0.01
0.99
0.95
Finished
Teacher S0
amrmousa-m
18h 56m 23s
-
-
4iktmwi4
-
PPO
0.2
0.01
0.01
0.99
0.95
0.001
0.00001
1
5
4
Adam
adaptive
true
1
elu
[512,256,128]
-
-
ActorCriticMlpDblEncExpert
100
[512,256,128]
1
20
[256,128,64]
1
-
-
-
-
clip
[256,128]
-
PPO
0.2
0.01
0.01
0.99
0.95
1-3
of 3