Rickstaa's group workspace
Group: han2020_reproduction_step_gpu
Name
10 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
ac_kwargs.activation
ac_kwargs.activation.actor
ac_kwargs.activation.critic
ac_kwargs.hidden_sizes.actor
ac_kwargs.hidden_sizes.critic
ac_kwargs.output_activation
ac_kwargs.output_activation.actor
ac_kwargs.output_activation.critic
actor_critic
adaptive_temperature
alpha
alpha3
batch_size
device
env
env_class
epochs
exp_name
export
gamma
horizon_length
labda
lr_a
lr_a_decay_type
lr_a_final
lr_alpha
lr_alpha_decay_type
lr_alpha_final
lr_c
lr_c_decay_type
lr_c_final
lr_decay_ref
lr_decay_type
lr_labda
lr_labda_decay_type
lr_labda_final
max_ep_len
num_test_episodes
opt_type
polyak
replay_size
save_freq
seed
Finished
-
rickstaa
pilot
1h 41m 13s
-
-
nn.ReLU
nn.ReLU
[256,256]
[64,64,16]
-
nn.ReLU
-
-
true
2
0.1
256
gpu
CartPoleCost-v1
stable_gym.envs.classic_control.cartpole_cost.cartpole_cost.CartPoleCost
489
han2020_reproduction_lac_cartpole_cost_alpha3_tune_exp_alp0-1
false
0.99
5
0.99
0.0001
-
1.0000e-10
-
-
-
0.0003
-
1.0000e-10
step
linear
-
-
-
250
10
minimize
0.995
1000000
10
48104
Finished
-
rickstaa
pilot
1h 43m 44s
-
-
nn.ReLU
nn.ReLU
[256,256]
[64,64,16]
-
nn.ReLU
-
-
true
2
0.2
256
gpu
CartPoleCost-v1
stable_gym.envs.classic_control.cartpole_cost.cartpole_cost.CartPoleCost
489
han2020_reproduction_lac_cartpole_cost_alpha3_tune_exp_alp0-2
false
0.99
5
0.99
0.0001
-
1.0000e-10
-
-
-
0.0003
-
1.0000e-10
step
linear
-
-
-
250
10
minimize
0.995
1000000
10
48104
Finished
-
rickstaa
pilot
1h 44m 27s
-
-
nn.ReLU
nn.ReLU
[256,256]
[64,64,16]
-
nn.ReLU
-
-
true
2
0.7
256
gpu
CartPoleCost-v1
stable_gym.envs.classic_control.cartpole_cost.cartpole_cost.CartPoleCost
489
han2020_reproduction_lac_cartpole_cost_alpha3_tune_exp_alp0-7
false
0.99
5
0.99
0.0001
-
1.0000e-10
-
-
-
0.0003
-
1.0000e-10
step
linear
-
-
-
250
10
minimize
0.995
1000000
10
48104
Finished
-
rickstaa
pilot
1h 42m 12s
-
-
nn.ReLU
nn.ReLU
[256,256]
[64,64,16]
-
nn.ReLU
-
-
true
2
1
256
gpu
CartPoleCost-v1
stable_gym.envs.classic_control.cartpole_cost.cartpole_cost.CartPoleCost
489
han2020_reproduction_lac_cartpole_cost_alpha3_tune_exp_alp1-0
false
0.99
5
0.99
0.0001
-
1.0000e-10
-
-
-
0.0003
-
1.0000e-10
step
linear
-
-
-
250
10
minimize
0.995
1000000
10
48104
Finished
-
rickstaa
pilot
1h 42m 1s
-
-
nn.ReLU
nn.ReLU
[256,256]
[64,64,16]
-
nn.ReLU
-
-
true
2
0.9
256
gpu
CartPoleCost-v1
stable_gym.envs.classic_control.cartpole_cost.cartpole_cost.CartPoleCost
489
han2020_reproduction_lac_cartpole_cost_alpha3_tune_exp_alp0-9
false
0.99
5
0.99
0.0001
-
1.0000e-10
-
-
-
0.0003
-
1.0000e-10
step
linear
-
-
-
250
10
minimize
0.995
1000000
10
48104
Finished
-
rickstaa
pilot
1h 41m 30s
-
-
nn.ReLU
nn.ReLU
[256,256]
[64,64,16]
-
nn.ReLU
-
-
true
2
0.3
256
gpu
CartPoleCost-v1
stable_gym.envs.classic_control.cartpole_cost.cartpole_cost.CartPoleCost
489
han2020_reproduction_lac_cartpole_cost_alpha3_tune_exp_alp0-3
false
0.99
5
0.99
0.0001
-
1.0000e-10
-
-
-
0.0003
-
1.0000e-10
step
linear
-
-
-
250
10
minimize
0.995
1000000
10
48104
Finished
-
rickstaa
pilot
1h 44m 6s
-
-
nn.ReLU
nn.ReLU
[256,256]
[64,64,16]
-
nn.ReLU
-
-
true
2
0.8
256
gpu
CartPoleCost-v1
stable_gym.envs.classic_control.cartpole_cost.cartpole_cost.CartPoleCost
489
han2020_reproduction_lac_cartpole_cost_alpha3_tune_exp_alp0-8
false
0.99
5
0.99
0.0001
-
1.0000e-10
-
-
-
0.0003
-
1.0000e-10
step
linear
-
-
-
250
10
minimize
0.995
1000000
10
48104
Finished
-
rickstaa
pilot
1h 46m 54s
-
-
nn.ReLU
nn.ReLU
[256,256]
[64,64,16]
-
nn.ReLU
-
-
true
2
0.4
256
gpu
CartPoleCost-v1
stable_gym.envs.classic_control.cartpole_cost.cartpole_cost.CartPoleCost
489
han2020_reproduction_lac_cartpole_cost_alpha3_tune_exp_alp0-4
false
0.99
5
0.99
0.0001
-
1.0000e-10
-
-
-
0.0003
-
1.0000e-10
step
linear
-
-
-
250
10
minimize
0.995
1000000
10
48104
Finished
-
rickstaa
pilot
2h 16m 15s
-
-
nn.ReLU
nn.ReLU
[256,256]
[64,64,16]
-
nn.ReLU
-
-
true
2
0.6
256
gpu
CartPoleCost-v1
stable_gym.envs.classic_control.cartpole_cost.cartpole_cost.CartPoleCost
489
han2020_reproduction_lac_cartpole_cost_alpha3_tune_exp_alp0-6
false
0.99
5
0.99
0.0001
-
1.0000e-10
-
-
-
0.0003
-
1.0000e-10
step
linear
-
-
-
250
10
minimize
0.995
1000000
10
48104
Finished
-
rickstaa
pilot
2h 16m 40s
-
-
nn.ReLU
nn.ReLU
[256,256]
[64,64,16]
-
nn.ReLU
-
-
true
2
0.5
256
gpu
CartPoleCost-v1
stable_gym.envs.classic_control.cartpole_cost.cartpole_cost.CartPoleCost
489
han2020_reproduction_lac_cartpole_cost_alpha3_tune_exp_alp0-5
false
0.99
5
0.99
0.0001
-
1.0000e-10
-
-
-
0.0003
-
1.0000e-10
step
linear
-
-
-
250
10
minimize
0.995
1000000
10
48104
1-10
of 10