Select runs that logged loss
to visualize data in this line chart.
to visualize data in this line chart.
Mountain Car Draft Offline RL Experiments
Created on February 28|Last edited on February 28
Comment
loss
loss
evaluation_reward
evaluation_reward
Select runs that logged evaluation_reward
to visualize data in this line chart.
to visualize data in this line chart.
Run set
0
Name
0 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
ALPHA
add_ha
algo.a2c.alpha
algo.a2c.beta
algo.a2c.blocker_epochs
algo.a2c.blocker_save_freq
algo.a2c.blocker_switch_time
algo.a2c.blocker_train_freq
algo.a2c.ent_coef
algo.a2c.eval_episodes
algo.a2c.eval_freq
algo.a2c.eval_seed
algo.a2c.exp_type
algo.a2c.gae_lambda
algo.a2c.gamma
algo.a2c.gif_freq
algo.a2c.learning_rate
algo.a2c.log_freq
algo.a2c.max_grad_norm
algo.a2c.n_steps
algo.a2c.normalize_advantage
algo.a2c.oversight_timesteps
algo.a2c.policy
algo.a2c.pretrained_blocker
algo.a2c.rms_prop_eps
algo.a2c.save_freq
algo.a2c.sde_sample_freq
algo.a2c.total_timesteps
algo.a2c.train_blocker
algo.a2c.use_blocker
algo.a2c.use_hirl
algo.a2c.use_rms_prop
algo.a2c.use_sde
algo.a2c.verbose
algo.a2c.vf_coef
algo.name
algo.ppo.alpha
algo.ppo.batch_size
algo.ppo.beta
algo.ppo.blocker_epochs
algo.ppo.blocker_save_freq
algo.ppo.blocker_switch_time
algo.ppo.blocker_train_freq
algo.ppo.clip_range
Finished
jaivdoshi
9h 38m 5s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
ppo
-
16
-
-
-
-
-
0.1
Finished
jaivdoshi
8h 39m 37s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
ppo
-
16
-
-
-
-
-
0.1
Finished
jaivdoshi
8h 14m 47s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
ppo
-
16
-
-
-
-
-
0.1
Finished
jaivdoshi
11h 57m 3s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
ppo
-
16
-
-
-
-
-
0.1
Finished
jaivdoshi
11h 56m 54s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
ppo
-
16
-
-
-
-
-
0.1
Finished
jaivdoshi
11h 56m 53s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
ppo
-
16
-
-
-
-
-
0.1
Finished
jaivdoshi
11h 57m 26s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
ppo
-
16
-
-
-
-
-
0.1
Finished
jaivdoshi
11h 57m 35s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
ppo
-
16
-
-
-
-
-
0.1
Finished
jaivdoshi
11h 57m 12s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
ppo
-
16
-
-
-
-
-
0.1
Finished
jaivdoshi
apr_test_2
4h 48m 48s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
ppo
-
16
-
-
-
-
-
0.1
1-10
of 2,344
Run set
0
Add a comment
Created with ❤️ on Weights & Biases.
https://wandb.ai/jaivdoshi/modified_hirl/reports/Mountain-Car-Draft-Offline-RL-Experiments--Vmlldzo2OTY1OTA3