Araffin's workspace
Runs
772
Name
772 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
algo
alpha
alpha_per
anneal_lr
autotune
batch_norm_momentum
batch_size
buffer_size
clip_coef
clip_grand_norm
clip_vloss
continuous_action
delay_policy_update
delta_adapt
delta_weight
device
drop_rate
dropout_rate
dyna
dyna_updates
dynamics_buffer_size
dynamics_ensemble_size
dynamics_min_uncertainty
dynamics_model_arch
dynamics_net_arch
dynamics_normalize_inputs
dynamics_num_elites
dynamics_real_ratio
dynamics_rollout_batch_size
dynamics_rollout_freq
dynamics_rollout_len
dynamics_rollout_starts
dynamics_train_freq
dynamics_uncertainty_threshold
ent_coef
env_id
epsilon_decay
epsilon_decay_steps
epsilon_decay_steps:
epsilon_ols
eval_freq
eval_mo_freq
evaluation_mode
evolutionary_iterations
Crashed
lnalegre
1h 28m 46s
-
GPI-LS Continuous Action - Jax
-
0.6
-
-
0.99
128
400000
-
-
-
-
-
-
-
-
-
0.01
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
mo-swimmer-v5
-
-
-
-
1000
10000
-
-
Crashed
lnalegre
1h 23m 15s
-
GPI-LS Continuous Action - Jax
-
0.6
-
-
0.99
128
400000
-
-
-
-
-
-
-
-
-
0.01
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
mo-walker2d-v5
-
-
-
-
1000
10000
-
-
Crashed
lnalegre
1h 28m 15s
-
GPI-LS Continuous Action - Jax
-
0.6
-
-
0.99
128
400000
-
-
-
-
-
-
-
-
-
0.01
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
mo-humanoid-v5
-
-
-
-
1000
10000
-
-
Crashed
lnalegre
1h 35m 17s
-
GPI-LS Continuous Action - Jax
-
0.6
-
-
0.99
128
400000
-
-
-
-
-
-
-
-
-
0.01
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
mo-humanoid-v5
-
-
-
-
1000
10000
-
-
Crashed
lnalegre
1h 51m 16s
-
GPI-LS Continuous Action - Jax
-
0.6
-
-
0.99
128
400000
-
-
-
-
-
-
-
-
-
0.01
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
mo-ant-v5
-
-
-
-
1000
10000
-
-
Killed
lnalegre
2h 2m 34s
-
GPI-LS Continuous Action - Jax
-
0.6
-
-
0.99
128
400000
-
-
-
-
-
-
-
-
-
0.01
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
mo-ant-v5
-
-
-
-
1000
10000
-
-
Killed
lnalegre
1h 30m 4s
-
GPI-LS Continuous Action - Jax
-
0.6
-
-
0.99
128
400000
-
-
-
-
-
-
-
-
-
0.01
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
mo-hopper-v5
-
-
-
-
1000
10000
-
-
Crashed
lnalegre
3h 51m 10s
-
GPI-LS Continuous Action - Jax
-
0.6
-
-
0.99
128
400000
-
-
-
-
-
-
-
-
-
0.01
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
mo-halfcheetah-v5
-
-
-
-
1000
10000
-
-
Killed
florian-felten
pr-104
23m 53s
-
PGMORL
-
-
false
-
-
8192
-
0.2
-
true
-
-
-
0.2
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
0
mo-halfcheetah-v4
-
-
-
-
-
-
-
20
Killed
florian-felten
pr-104
4m 13s
-
PGMORL
-
-
false
-
-
8192
-
0.2
-
true
-
-
-
0.2
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
0
mo-halfcheetah-v4
-
-
-
-
-
-
-
20
Finished
lnalegre
pr-104
1h 59m 56s
-
PCN
-
-
-
-
-
256
-
-
-
-
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
minecart-v0
-
-
-
-
-
-
-
-
Finished
lnalegre
pr-104
54m 48s
-
PCN
-
-
-
-
-
256
-
-
-
-
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
minecart-deterministic-v0
-
-
-
-
-
-
-
-
Crashed
lnalegre
1d 15h 56m 4s
-
GPI-LS - Jax
-
0.6
-
-
-
128
100000
-
-
-
-
-
-
-
-
0
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
mo-supermario-v0
-
-
10000
-
1000
10000
-
-
Crashed
lnalegre
1h 12m 6s
-
GPI-LS - Jax
-
0.6
-
-
-
128
100000
-
-
-
-
-
-
-
-
0
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
mo-supermario-v0
-
-
10000
-
1000
10000
-
-
Crashed
lnalegre
1h 13m 31s
-
GPI-LS - Jax
-
0.6
-
-
-
128
100000
-
-
-
-
-
-
-
-
0
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
mo-supermario-v0
-
-
10000
-
1000
10000
-
-
Failed
lnalegre
7h 25m 18s
-
GPI-LS - Jax
-
0.6
-
-
-
128
100000
-
-
-
-
-
-
-
-
0
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
mo-supermario-v0
-
-
10000
-
1000
10000
-
-
Failed
lnalegre
8h 12m 7s
-
GPI-LS - Jax
-
0.6
-
-
-
128
100000
-
-
-
-
-
-
-
-
0
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
mo-supermario-v0
-
-
10000
-
1000
10000
-
-
Crashed
lnalegre
pr-95
1d 15h 58m 8s
-
GPI-LS Continuous Action
0.6
-
-
-
-
128
400000
-
-
-
-
2
-
-
-
-
-
false
-
-
-
2
-
[200,200,200,200]
-
-
0.1
50000
250
5
1000
250
-
-
mo-humanoid-v4
-
-
-
-
1000
10000
-
-
Crashed
lnalegre
pr-95
16h 52m 34s
-
GPI-LS Continuous Action
0.6
-
-
-
-
128
400000
-
-
-
-
2
-
-
-
-
-
false
-
-
-
2
-
[200,200,200,200]
-
-
0.1
50000
250
5
1000
250
-
-
mo-humanoid-v4
-
-
-
-
1000
10000
-
-
Crashed
lnalegre
pr-95
19h 18m 35s
-
GPI-LS Continuous Action
0.6
-
-
-
-
128
400000
-
-
-
-
2
-
-
-
-
-
false
-
-
-
2
-
[200,200,200,200]
-
-
0.1
50000
250
5
1000
250
-
-
mo-ant-v4
-
-
-
-
1000
10000
-
-
1-20
of 772