Dominik_roth's workspace
Runs
27
Name
27 visualized
algo.actor.hidden_layers: 512
algo.actor.hidden_layers: 512
3
9
algo.actor.hidden_layers: 256
algo.actor.hidden_layers: 256
3
9
algo.actor.hidden_layers: 64
algo.actor.hidden_layers: 64
3
9
1-3
of 3Charts
1
Episode_Reward
16
Episode_Termination
2
Metrics
2
train
13
train/return
train/return
algo.actor.hidden_layers: [512,512,512,512], algo.critic.hidden_layers: [512,512,512,512]
algo.actor.hidden_layers: [512,512,512,512], algo.critic.hidden_layers: [64,64]
algo.actor.hidden_layers: [256,256], algo.critic.hidden_layers: [512,512,512,512]
algo.actor.hidden_layers: [512,512,512,512], algo.critic.hidden_layers: [256,256]
algo.actor.hidden_layers: [256,256], algo.critic.hidden_layers: [256,256]
algo.actor.hidden_layers: [256,256], algo.critic.hidden_layers: [64,64]
algo.actor.hidden_layers: [64,64], algo.critic.hidden_layers: [512,512,512,512]
algo.actor.hidden_layers: [64,64], algo.critic.hidden_layers: [64,64]
algo.actor.hidden_layers: [64,64], algo.critic.hidden_layers: [256,256]
train/kl_divergence
train/kl_divergence
algo.actor.hidden_layers: [512,512,512,512], algo.critic.hidden_layers: [512,512,512,512]
algo.actor.hidden_layers: [512,512,512,512], algo.critic.hidden_layers: [64,64]
algo.actor.hidden_layers: [256,256], algo.critic.hidden_layers: [512,512,512,512]
algo.actor.hidden_layers: [512,512,512,512], algo.critic.hidden_layers: [256,256]
algo.actor.hidden_layers: [256,256], algo.critic.hidden_layers: [256,256]
algo.actor.hidden_layers: [256,256], algo.critic.hidden_layers: [64,64]
algo.actor.hidden_layers: [64,64], algo.critic.hidden_layers: [512,512,512,512]
algo.actor.hidden_layers: [64,64], algo.critic.hidden_layers: [64,64]
algo.actor.hidden_layers: [64,64], algo.critic.hidden_layers: [256,256]