change parameter

rl_game/get_up/config/ppo_cfg.yaml

@@ -41,19 +41,19 @@ params:
     normalize_advantage: True
     gamma: 0.99
     tau: 0.95
-    learning_rate: 3e-4
+    learning_rate: 2e-4
     lr_schedule: adaptive
     kl_threshold: 0.008
     score_to_win: 20000
     max_epochs: 500000
     save_best_after: 50
     save_frequency: 100
-    grad_norm: 1.0
-    entropy_coef: 0.05
+    grad_norm: 0.5
+    entropy_coef: 0.005
     truncate_grads: True
     bounds_loss_coef: 0.001
     e_clip: 0.2
-    horizon_length: 64
+    horizon_length: 32
     minibatch_size: 4096
     mini_epochs: 5
     critic_coef: 1

rl_game/get_up/config/t1_env_cfg.py

@@ -1,5 +1,4 @@
 import random
-
 import numpy
 import numpy as np
 import torch
@@ -343,7 +342,7 @@ class T1GetUpRewardCfg:
     # 7. 成功终极大奖
     is_success = RewTerm(
         func=lambda env, keys: env.termination_manager.get_term(keys),
-        weight=1000.0,
+        weight=300.0,
         params={"keys": "standing_success"}
     )
 
@@ -383,4 +382,4 @@ class T1EnvCfg(ManagerBasedRLEnvCfg):
     actions = T1ActionCfg()
 
     episode_length_s = 6.0
-    decimation = 4
+    decimation = 2