Comment
Section 1
a2cv vs ppo
a2cv vs ppo
Run set 1
6
Name
6 visualized
State
User
Tags
Created
Runtime
Sweep
exp_name
seed
charts/episode_reward
global_step
gym_id
_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
algorithm_spec.eps_start
algorithm_spec.gamma
algorithm_spec.lambda
algorithm_spec.max_grad_norm
algorithm_spec.multi_step
algorithm_spec.policy_loss_coeff
algorithm_spec.replay_buffer_size
algorithm_spec.target_update_interval
algorithm_spec.vf_coeff
alpha
anneal-lr
anneal_lr
architectures
Finished
costa-huang
33s
-
-
-
-
100
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Finished
costa-huang
1m 5s
-
-
42
-
-
-
EleutherAI/pythia-160m
-
true
false
true
-
-
-
-
-
false
0.9
0.999
1.0000e-8
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
["GPTNeoXForCausalLM"]
Failed
costa-huang
52s
-
-
42
-
-
-
EleutherAI/pythia-160m
-
true
false
true
-
-
-
-
-
false
0.9
0.999
1.0000e-8
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
["GPTNeoXForCausalLM"]
Killed
costa-huang
1m 18s
-
-
42
-
-
-
EleutherAI/pythia-160m
-
true
false
true
-
-
-
-
-
false
0.9
0.999
1.0000e-8
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
["GPTNeoXForCausalLM"]
Failed
costa-huang
24s
-
-
42
-
-
-
EleutherAI/pythia-160m
-
true
false
true
-
-
-
-
-
false
0.9
0.999
1.0000e-8
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
["GPTNeoXForCausalLM"]
Failed
costa-huang
1m 34s
-
-
42
-
-
-
EleutherAI/pythia-160m
-
true
false
true
-
-
-
-
-
false
0.9
0.999
1.0000e-8
false
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
["GPTNeoXForCausalLM"]
Finished
costa-huang
14m 27s
-
main
42
-
149481
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Crashed
costa-huang
40m 34s
-
train_policy_pipeline7
1
-
350208
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Crashed
costa-huang
21m 9s
-
train_policy_pipeline6
1
-
55808
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Failed
costa-huang
1h 36m
-
train_policy1
1
-
999936
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
1-10
of 4,883
Add a comment
Created with ❤️ on Weights & Biases.
https://wandb.ai/costa-huang/cleanRL/reports/cartpolev0-a2cv-ppo--VmlldzoyMTk4NA