Hamzadata's workspace
Runs
3
State
Notes
User
Tags
Created
Runtime
Sweep
anneal_lr
batch_size
buffer_size
capture_video
checkpoint_freq
clip_coef
clip_vloss
cuda
end_e
ent_coef
env_id
eval_episodes
exp_name
exploration_fraction
gae_lambda
gamma
learning_rate
learning_starts
max_grad_norm
minibatch_size
norm_adv
num_envs
num_iterations
num_minibatches
num_steps
save_model
seed
start_e
target_network_frequency
tau
torch_deterministic
total_timesteps
track
train_frequency
update_epochs
vf_coef
wandb_entity
wandb_project_name
charts/SPS
charts/episodic_length
charts/episodic_return
charts/learning_rate
eval/episodic_return
global_step
Finished
PPO (lr = 2.5e-4
hamzadata
3h 24m 36s
-
true
1024
-
true
1000
0.1
true
true
-
0.01
PongNoFrameskip-v4
10
ppo-pong
-
0.95
0.99
0.00025
-
0.5
256
true
8
4394
4
128
true
3
-
-
-
true
4500000
true
-
4
0.5
hamzalab
rl-lab
372
13366
15
5.6896e-8
20
4499456
Finished
DQN
hamzadata
13h 47s
-
-
32
500000
true
-
-
-
true
0.01
-
PongNoFrameskip-v4
10
dqn-pong
0.1
-
0.99
0.0001
80000
-
-
-
1
-
-
-
true
3
1
1000
1
true
3000000
true
4
-
-
hamzalab
rl-lab
69
7840
17
-
17
2999900
Finished
PPO (lr = 2.5e-3
hamzadata
3h 38m 28s
-
true
1024
-
true
1000
0.1
true
true
-
0.01
PongNoFrameskip-v4
10
ppo-pong
-
0.95
0.99
0.0025
-
0.5
256
true
8
4394
4
128
true
3
-
-
-
true
4500000
true
-
4
0.5
hamzalab
rl-lab
349
10133
21
5.6896e-7
20
4499456
1-3
of 3