Regression Report: ddpg_continuous_action (['pr-299', 'rlops-pilot'])
Created on November 1|Last edited on November 1
Comment
Hopper-v2
Hopper-v2
Hopper-v2
Hopper-v2
CleanRL's ddpg_continuous_action (pr-299)
3
CleanRL's ddpg_continuous_action (rlops-pilot)
3
Name
3 visualized
exp_name: ddpg_continuous_action
exp_name: ddpg_continuous_action
3
State
Notes
User
Tags
Created
Runtime
Sweep
actor_device_ids
actor_devices
adv_norm_fullbatch
alpha
anneal_lr
anneal_steps
async_batch_size
async_update
autotune
aux_batch_rollouts
backend
base_model
batch_size
beta_clone
buffer_size
capture_video
channels
clip_coef
clip_vloss
concurrency
cuda
debug_normalize
deepspeed
device_ids
discount
distill_batch_size
distill_beta
distill_learning_rate
distill_update_epochs
distributed
dropout_rate
e_auxiliary
e_policy
end_e
ent_coef
env
env_id
eps
eval_every
eval_freq
exp_name
expl_noise
exploration_fraction
exploration_noise
Finished
costa-huang
3h 25m 30s
-
-
-
-
-
-
-
-
-
-
-
-
-
256
-
1000000
true
-
-
-
-
true
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Hopper-v2
-
-
-
ddpg_continuous_action
-
-
0.1
1-1
of 1
CleanRL's ddpg_continuous_action (pr-299)
3
CleanRL's ddpg_continuous_action (rlops-pilot)
3
CleanRL's ddpg_continuous_action (pr-299)
3
CleanRL's ddpg_continuous_action (rlops-pilot)
3
Add a comment
Created with ❤️ on Weights & Biases.
https://wandb.ai/openrlbenchmark/cleanrl-cache/reports/Regression-Report-ddpg_continuous_action-pr-299-rlops-pilot---VmlldzoyODkyNTcy