Change test_SB3_policy.py name to exploit_SB3_policy.py

LIHPC-Computational-Geometry · Jan 9, 2025 · abf4079 · abf4079
1 parent b494193
commit abf4079
Show file tree

Hide file tree

Showing 4 changed files with 6 additions and 5 deletions.
diff --git a/test_SB3_policy.py → exploit_SB3_policy.py b/test_SB3_policy.py → exploit_SB3_policy.py
@@ -84,7 +84,7 @@ def isBetterMesh(best_mesh, actual_mesh):
     else:
         return False
 
-
+"""
 dataset = [TM.random_mesh(30) for _ in range(9)]
 with open("environment/parameters/environment_config.json", "r") as f:
     env_config = json.load(f)
@@ -94,3 +94,4 @@ def isBetterMesh(best_mesh, actual_mesh):
 
 plot_test_results(avg_rewards, avg_wins, avg_steps, avg_normalized_return)
 plot_dataset(final_meshes)
+"""
diff --git a/model_RL/parameters/ppo_config.json b/model_RL/parameters/ppo_config.json
@@ -6,6 +6,6 @@
     "learning_rate": 0.0001,
     "gamma": 0.9,
     "verbose": 1,
-    "tensorboard_log": "./results/final/",
-    "total_timesteps": 1000000
+    "tensorboard_log": "./results/test/",
+    "total_timesteps": 5000
 }
diff --git a/train_SB3.py b/train_SB3.py
@@ -6,7 +6,7 @@
 from environment.gymnasium_envs.trimesh_full_env import TriMeshEnvFull
 import mesh_model.random_trimesh as TM
 from plots.mesh_plotter import dataset_plt
-from test_SB3_policy import testPolicy
+from exploit_SB3_policy import testPolicy
 from stable_baselines3 import PPO,SAC
 from stable_baselines3.common.env_checker import check_env
 from stable_baselines3.common.callbacks import BaseCallback

diff --git a/train_SB3_flip.py b/train_SB3_flip.py
@@ -6,7 +6,7 @@
 from environment.gymnasium_envs.trimesh_flip_env import TriMeshEnvFlip
 import mesh_model.random_trimesh as TM
 from plots.mesh_plotter import dataset_plt
-from test_SB3_policy import testPolicy
+from exploit_SB3_policy import testPolicy
 from stable_baselines3 import PPO, SAC
 from stable_baselines3.common.env_checker import check_env
 from stable_baselines3.common.callbacks import BaseCallback