Hugging Face's logo

skrl
/
OmniIsaacGymEnvs-ShadowHand-PPO

Reinforcement Learning
skrl
deep-reinforcement-learning
Eval Results
Model card Files Community
7
jow2 commited on
Commit
fdc16b7
·
1 Parent(s): 9c2f7cb

Experiment3

Browse files
Files changed (1) hide show
  1. README.md → Experiment3 +1 -1
README.md → Experiment3 RENAMED
@@ -41,7 +41,7 @@ agent.load(path)
41
  ```python
42
  # https://skrl.readthedocs.io/en/latest/modules/skrl.agents.ppo.html#configuration-and-hyperparameters
43
  cfg_ppo = PPO_DEFAULT_CONFIG.copy()
44
- cfg_ppo["rollouts"] = 16 # memory_size
45
  cfg_ppo["learning_epochs"] = 5
46
  cfg_ppo["mini_batches"] = 4 # 16 * 8192 / 32768
47
  cfg_ppo["discount_factor"] = 0.99
 
41
  ```python
42
  # https://skrl.readthedocs.io/en/latest/modules/skrl.agents.ppo.html#configuration-and-hyperparameters
43
  cfg_ppo = PPO_DEFAULT_CONFIG.copy()
44
+ cfg_ppo["rollouts"] = 20 # memory_size
45
  cfg_ppo["learning_epochs"] = 5
46
  cfg_ppo["mini_batches"] = 4 # 16 * 8192 / 32768
47
  cfg_ppo["discount_factor"] = 0.99