first commit

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Walker": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 300000, "time_horizon": 1000, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/windows/Walker/Walker", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Walker Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Walker": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 300000, "time_horizon": 1000, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "Walker", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Walker Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -45,7 +45,7 @@ behaviors:
     self_play: null
     behavioral_cloning: null
 env_settings:
-  env_path: ./training-envs-executables/windows/Walker/Walker
+  env_path: Walker
   env_args: null
   base_port: 5005
   num_envs: 1

run_logs/timers.json

@@ -2,44 +2,44 @@
     "name": "root",
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1722625854",
+        "start_time_seconds": "1722627021",
         "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Walker.yaml --env=./training-envs-executables/windows/Walker/Walker --run-id=Walker Training --no-graphics --resume",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Walker.yaml --env=Walker --run-id=Walker Training --no-graphics --resume",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.3.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1722625854"
+        "end_time_seconds": "1722627021"
     },
-    "total": 0.11044819199992162,
+    "total": 0.1743355169996903,
     "count": 1,
-    "self": 0.012869786999999633,
+    "self": 0.029275382999912836,
     "children": {
         "run_training.setup": {
-            "total": 0.07346703000007437,
+            "total": 0.1067342460000873,
             "count": 1,
-            "self": 0.07346703000007437
+            "self": 0.1067342460000873
         },
         "TrainerController.start_learning": {
-            "total": 0.024111374999847612,
+            "total": 0.03832588799969017,
             "count": 1,
-            "self": 0.0008246849999977712,
+            "self": 0.0008429109993812745,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 0.02324155599990263,
+                    "total": 0.037428019999879325,
                     "count": 1,
-                    "self": 0.02324155599990263
+                    "self": 0.037428019999879325
                 },
                 "trainer_threads": {
-                    "total": 2.0249999579391442e-06,
+                    "total": 2.1190003280935343e-06,
                     "count": 1,
-                    "self": 2.0249999579391442e-06
+                    "self": 2.1190003280935343e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 4.310899998927198e-05,
+                    "total": 5.283800010147388e-05,
                     "count": 1,
-                    "self": 4.310899998927198e-05
+                    "self": 5.283800010147388e-05
                 }
             }
         }