Hugging Face's logo

skrl
/
OmniIsaacGymEnvs-Humanoid-PPO

Reinforcement Learning
skrl
deep-reinforcement-learning
Eval Results
Model card Files Community
1
jow2 commited on
Commit
69bc062
·
1 Parent(s): b8cfce4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -45,7 +45,7 @@ cfg_ppo["rollouts"] = 32 # memory_size
45
  cfg_ppo["learning_epochs"] = 5
46
  cfg_ppo["mini_batches"] = 4 # 32 * 4096 / 32768
47
  cfg_ppo["discount_factor"] = 0.99
48
- cfg_ppo["lambda"] = 0.95
49
  cfg_ppo["learning_rate"] = 5e-4
50
  cfg_ppo["learning_rate_scheduler"] = KLAdaptiveRL
51
  cfg_ppo["learning_rate_scheduler_kwargs"] = {"kl_threshold": 0.008}
 
45
  cfg_ppo["learning_epochs"] = 5
46
  cfg_ppo["mini_batches"] = 4 # 32 * 4096 / 32768
47
  cfg_ppo["discount_factor"] = 0.99
48
+ cfg_ppo["lambda"] = 0.90
49
  cfg_ppo["learning_rate"] = 5e-4
50
  cfg_ppo["learning_rate_scheduler"] = KLAdaptiveRL
51
  cfg_ppo["learning_rate_scheduler_kwargs"] = {"kl_threshold": 0.008}