Comment
HalfCheetah-v2
HalfCheetah-v2
CleanRL's td3_continuous_action_jax.py (VM w/ TPU) #285
CleanRL's td3_continuous_action_jax.py (VM w/ TPU)
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI) #285
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI)
HalfCheetah-v2
HalfCheetah-v2
CleanRL's td3_continuous_action_jax.py (VM w/ TPU) #285
CleanRL's td3_continuous_action_jax.py (VM w/ TPU)
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI) #285
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI)
CleanRL's td3_continuous_action_jax.py (VM w/ TPU) #285
3
CleanRL's td3_continuous_action_jax.py (VM w/ TPU)
3
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI) #285
3
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI)
3
Name
3 visualized
env_id: HalfCheetah-v2
env_id: HalfCheetah-v2
1
3
State
Notes
User
Tags
Created
Runtime
Sweep
anneal_lr
batch_size
buffer_size
capture_video
clip_coef
clip_vloss
cuda
end_e
ent_coef
env_id
exp_name
exploration_fraction
exploration_noise
gae
gae_lambda
gamma
learning_rate
learning_starts
max_grad_norm
minibatch_size
noise_clip
norm_adv
num_envs
num_minibatches
num_steps
policy_frequency
seed
start_e
target_network_frequency
tau
torch_deterministic
total_timesteps
track
train_frequency
update_epochs
vf_coef
wandb_entity
wandb_project_name
adv_norm_fullbatch
alpha
autotune
aux_batch_rollouts
Finished
costa-huang
2h 49m 11s
-
-
256
1000000
true
-
-
-
-
-
HalfCheetah-v2
td3_continuous_action_jax
-
0.1
-
-
0.99
0.0003
25000
-
-
0.5
-
-
-
-
2
3
-
-
0.005
-
1000000
true
-
-
-
-
cleanRL
-
-
-
-
1-1
of 1
CleanRL's td3_continuous_action_jax.py (VM w/ TPU) #285
3
CleanRL's td3_continuous_action_jax.py (VM w/ TPU)
3
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI) #285
3
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI)
6
CleanRL's td3_continuous_action_jax.py (VM w/ TPU) #285
3
CleanRL's td3_continuous_action_jax.py (VM w/ TPU)
3
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI) #285
3
CleanRL's td3_continuous_action_jax.py (RTX 3060 TI)
6
Add a comment
Created with ❤️ on Weights & Biases.
https://wandb.ai/openrlbenchmark/cleanrl-cache/reports/-285-MuJoCo-CleanRL-s-TD3-JAX--VmlldzoyODI2ODIy