Select runs that logged charts/episodic_return
to visualize data in this line chart.
to visualize data in this line chart.
Comment
HalfCheetah-v2
HalfCheetah-v2
Run set
3
Run set 2
9
Name
9 visualized
env_id: HalfCheetah-v2
env_id: HalfCheetah-v2
15
133
State
Notes
User
Tags
Created
Runtime
Sweep
anneal_lr
batch_size
buffer_size
capture_video
clip_coef
clip_vloss
cuda
discount
end_e
ent_coef
env
env_id
eval_freq
exp_name
expl_noise
exploration_fraction
exploration_noise
gae
gae_lambda
gamma
learning_rate
learning_starts
load_model
max_grad_norm
max_timesteps
minibatch_size
n_atoms
noise_clip
norm_adv
num_envs
num_minibatches
num_steps
policy
policy_freq
policy_frequency
policy_noise
save_model
seed
start_e
start_timesteps
target_network_frequency
tau
torch_deterministic
total_timesteps
Finished
-
costa-huang
18mo 16d 13h 57m 4s
-
true
1104.84211
1000000
[false,true]
0.2
true
[false,true]
-
-
0
-
HalfCheetah-v2
6249.25
["ddpg_continuous_action","ddpg_continuous_action_jax","ppo_continuous_action_8M","rpo_continuous_action","rpo_continuous_action_alpha_0_01","rpo_continuous_action_alpha_0_05","rpo_continuous_action_alpha_0_1","sac_continuous_action","td3_continuous_action","td3_continuous_action_jax"]
-
-
0.1
true
0.95
0.99
0.0003
18714.28571
-
0.5
-
64
-
0.5
true
1
32
2048
-
-
1.9
0.2
-
3.30827
-
-
1
0.005
true
3631578.94737
1-1
of 1
Run set
3
Run set 2
9
Run set
9
Run set 2
1
Add a comment
Created with ❤️ on Weights & Biases.
https://wandb.ai/costa-huang/cleanRL/reports/MuJoCo-sfujim-TD3-Vs-CleanRL--VmlldzoxNzI0OTcy