Skip to main content

Test

Created on March 7|Last edited on March 7

100k200k300k400kglobal_step-500-400-300-200-100
Run set
1
Run set 2
1
State
Notes
User
Tags
Created
Runtime
Sweep
ent_coef
episode_length
exp_name
gamma
gym_id
learning_rate
max_grad_norm
prod_mode
seed
torch_deterministic
total_timesteps
vf_coef
wandb_project_name
charts/episode_reward
global_step
losses/entropy
losses/policy_loss
losses/value_loss
Finished
Oct12_03-00-37__a2c__1
costa-huang
1m 24s
-
0.01
200
a2c
0.99
CartPole-v0
0.0007
0.5
true
1
true
50000
0.25
cleanrltest
187
50033
0.50384
15.01714
387.56595
1-1
of 1