Adhiisetiawan's workspace
Runs
2
State
Notes
User
Tags
Created
Runtime
Sweep
anneal_lr
batch_size
capture_video
clip_coef
clip_vloss
cuda
ent_coef
exp_name
gae
gae_lambda
gamma
gym_id
learning_rate
max_grad_norm
minibatch_size
norm_adv
num_envs
num_minibatches
num_steps
seed
torch_deterministic
total_timesteps
track
update_epochs
vf_coef
wandb_project_name
charts/SPS
charts/episodic_length
charts/episodic_return
charts/learning_rate
global_step
losses/approx_kl
losses/clipfrac
losses/entropy
losses/explained_variance
losses/old_approx_kl
losses/policy_loss
losses/value_loss
Finished
-
adhiisetiawan
3m 35s
-
true
2048
true
0.2
true
true
0.01
ppo
true
0.95
0.99
CartPole-v1
0.00025
0.5
512
true
16
4
128
1
true
1000000
true
4
0.5
ppo-algorithm
5053
500
500
5.1230e-7
999424
1.0827e-8
0
0.49092
0.27733
-0.000003007
-0.0000024913
62.96896
Finished
-
adhiisetiawan
17m 10s
-
true
2048
true
0.2
true
true
0.01
ppo
true
0.95
0.99
LunarLander-v2
0.00025
0.5
512
true
16
4
128
1
true
1000000
true
4
0.5
ppo-algorithm
982
1000
-46.38069
5.1230e-7
999424
7.8813e-8
0
0.96693
0.62167
-0.000010126
-0.000010096
4.69717
1-2
of 2