Comment
a2cv vs ppo vs a2c
charts/episode_reward
charts/episode_reward
Run set 1
9
Name
9 visualized
State
Notes
User
Tags
Created
Runtime
Sweep
clip_coef
end_e
ent_coef
episode_length
exp_name
exploration_duration
exploration_fraction
gamma
gym_id
learning_rate
max_grad_norm
prod_mode
seed
start_e
torch_deterministic
total_timesteps
update_frequency
vf_coef
_name_or_path
a
accelerator_config.even_batches
accelerator_config.split_batches
accelerator_config.use_seedable_sampler
action_noise
action_shape
actor_buffer_size
actor_device_ids
actor_devices
adafactor
adam_beta1
adam_beta2
adam_epsilon
add_cross_attention
agent_model_path
alg
algorithm
algorithm_spec.GAE
algorithm_spec.K_epoch
algorithm_spec.dueling
algorithm_spec.entropy_coeff
algorithm_spec.episodic_update
algorithm_spec.eps_clip
algorithm_spec.eps_decay
algorithm_spec.eps_final
Finished
-
costa-huang
33s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Finished
-
costa-huang
1m 5s
-
-
-
-
-
-
-
-
-
-
0.00005
1
-
42
-
-
-
-
-
EleutherAI/pythia-160m
-
true
false
true
-
-
-
-
-
false
0.9
0.999
1.0000e-8
false
-
-
-
-
-
-
-
-
-
-
-
Failed
-
costa-huang
52s
-
-
-
-
-
-
-
-
-
-
0.00005
1
-
42
-
-
-
-
-
EleutherAI/pythia-160m
-
true
false
true
-
-
-
-
-
false
0.9
0.999
1.0000e-8
false
-
-
-
-
-
-
-
-
-
-
-
Killed
-
costa-huang
1m 18s
-
-
-
-
-
-
-
-
-
-
0.00005
1
-
42
-
-
-
-
-
EleutherAI/pythia-160m
-
true
false
true
-
-
-
-
-
false
0.9
0.999
1.0000e-8
false
-
-
-
-
-
-
-
-
-
-
-
Failed
-
costa-huang
24s
-
-
-
-
-
-
-
-
-
-
0.00005
1
-
42
-
-
-
-
-
EleutherAI/pythia-160m
-
true
false
true
-
-
-
-
-
false
0.9
0.999
1.0000e-8
false
-
-
-
-
-
-
-
-
-
-
-
Failed
-
costa-huang
1m 34s
-
-
-
-
-
-
-
-
-
-
0.00005
1
-
42
-
-
-
-
-
EleutherAI/pythia-160m
-
true
false
true
-
-
-
-
-
false
0.9
0.999
1.0000e-8
false
-
-
-
-
-
-
-
-
-
-
-
Finished
-
costa-huang
14m 27s
-
-
-
-
-
main
-
-
-
-
-
-
-
42
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Crashed
-
costa-huang
40m 34s
-
-
-
-
-
train_policy_pipeline7
-
-
-
-
-
-
-
1
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Crashed
-
costa-huang
21m 9s
-
-
-
-
-
train_policy_pipeline6
-
-
-
-
-
-
-
1
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Failed
-
costa-huang
1h 36m
-
-
-
-
-
train_policy1
-
-
-
-
-
-
-
1
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
1-10
of 4,883
Add a comment
Created with ❤️ on Weights & Biases.
https://wandb.ai/costa-huang/cleanRL/reports/taxi-v2-a2cv-ppo-a2c--VmlldzoyMTk4Mw