Comment
training/side_effects
training/side_effects
Run set
8
State
Notes
User
Tags
Created
Runtime
Sweep
DQN.gamma
DQN.learning_rate
DQN.multi_step_learning
DQN.optimize_interval
DQN.replay_initial
DQN.replay_size
DQN.target_update_interval
DQN.training_batch_size
PPO.entropy_clip
PPO.entropy_reg
PPO.epochs_per_batch
PPO.eps_policy
PPO.eps_value
PPO.gamma
PPO.learning_rate
PPO.lmda
PPO.num_minibatches
PPO.steps_per_env
PPO.vf_coef
SafeLifePolicyNetwork.dense_depth
SafeLifePolicyNetwork.dense_width
algo
data_dir
deterministic
env.exit_difficulty.t
env.exit_difficulty.y
env.task_switch.t
env.task_switch.y
env.view_size
env_type
human_play
run_type
seed
side_effect.baseline
side_effect.penalty
side_effect.schedule.t
side_effect.schedule.y
steps
validation.env_seed
validation.num_levels
avg_length
benchmark/episodes
benchmark/length
benchmark/length_avg
Finished
stacey
navigate
54m 54s
-
-
-
-
-
-
-
-
-
1
0.01
3
0.05
0.4
0.97
0.0003
0.95
4
20
0.5
1
512
ppo
nav_eps_p_0.05_v_0.4
false
[500000,2000000]
[0.001,1]
-
-
25
navigate
-
train
5754375288425975
starting-state
0
[1000000,2000000]
[0,1]
1000000
732230218323780600
5
156.292
1000
949
156.292
Finished
stacey
navigate
57m 58s
-
-
-
-
-
-
-
-
-
1
0.01
3
0.1
0.3
0.97
0.0003
0.95
4
20
0.5
1
512
ppo
nav_eps_p_0.1_v_0.3
false
[500000,2000000]
[0.001,1]
-
-
25
navigate
-
train
1622432676049203
starting-state
0
[1000000,2000000]
[0,1]
1000000
732230218323780600
5
107.436
1000
1000
107.436
Finished
stacey
display_vid
navigate
41m 2s
-
-
-
-
-
-
-
-
-
1
0.01
3
0.3
0.1
0.97
0.0003
0.95
4
20
0.5
1
512
ppo
nav_eps_p_0.3_v_0.1
false
[500000,2000000]
[0.001,1]
-
-
25
navigate
-
train
4891633426165854
starting-state
0
[1000000,2000000]
[0,1]
1000000
732230218323780600
5
179.209
1000
1000
179.209
Finished
stacey
display_vid
navigate
37m 35s
-
-
-
-
-
-
-
-
-
1
0.01
6
0.2
0.2
0.97
0.0003
0.95
8
40
0.5
1
512
ppo
navigate_double
false
[500000,2000000]
[0.001,1]
-
-
25
navigate
-
train
6853708267308291
starting-state
0
[1000000,2000000]
[0,1]
1000000
732230218323780600
5
361.512
1000
994
361.512
Finished
stacey
display_vid
navigate
14h 32m 3s
-
-
-
-
-
-
-
-
-
1
0.01
3
0.2
0.2
0.97
0.0003
0.95
4
20
0.5
1
512
ppo
navigate_6M
false
[500000,2000000]
[0.001,1]
-
-
25
navigate
-
train
7751382880903765
starting-state
0
[1000000,2000000]
[0,1]
6000000
732230218323780600
5
52.24
1000
1000
52.24
Finished
stacey
display_vid
dqn
49m 8s
-
0.97
0.0003
5
32
40000
100000
10000
96
-
-
-
-
-
-
-
-
-
-
-
1
512
dqn
navigate_1M_dqn
false
[500000,2000000]
[0.001,1]
-
-
25
navigate
-
train
6470616393261732
starting-state
0
[1000000,2000000]
[0,1]
1000000
732230218323780600
5
231.987
1000
1000
231.987
Finished
stacey
display_vid
navigate
1h 4m 4s
-
-
-
-
-
-
-
-
-
1
0.01
3
0.2
0.2
0.97
0.0003
0.95
4
20
0.5
1
512
ppo
navigate-spawn_1M
false
[500000,2000000]
[0.001,1]
-
-
25
navigate
-
train
3962160720871220
starting-state
0
[1000000,2000000]
[0,1]
1000000
732230218323780600
5
140.018
1000
1000
140.018
Finished
stacey
test
16m 42s
-
-
-
-
-
-
-
-
-
1
0.01
3
0.2
0.2
0.97
0.0003
0.95
4
20
0.5
1
512
ppo
navigate_test
false
[500000,2000000]
[0.001,1]
-
-
25
navigate
-
train
3983135968675229
starting-state
0
[1000000,2000000]
[0,1]
1000
732230218323780600
5
973.566
1000
1000
973.566
1-8
of 8
Add a comment
Created with ❤️ on Weights & Biases.
https://wandb.ai/stacey/saferlife/reports/Test-Report--Vmlldzo2NDE0MDY