{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8372166156768799, "min": 0.8372166156768799, "max": 2.868605852127075, "count": 25 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8491.05078125, "min": 8173.58740234375, "max": 28369.04296875, "count": 25 }, "SnowballTarget.Step.mean": { "value": 249984.0, "min": 9992.0, "max": 249984.0, "count": 25 }, "SnowballTarget.Step.sum": { "value": 249984.0, "min": 9992.0, "max": 249984.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.314830780029297, "min": 0.3329489529132843, "max": 13.314830780029297, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2596.39208984375, "min": 50.60824203491211, "max": 2709.8662109375, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 6567.0, "max": 10945.0, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06597066568921196, "min": 0.0603534837192616, "max": 0.0771063272653907, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26388266275684785, "min": 0.23131898179617208, "max": 0.3597804722113663, "count": 25 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1804471536375144, "min": 0.10131556646947086, "max": 0.29793158129734154, "count": 25 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7217886145500576, "min": 0.30394669940841257, "max": 1.4112404035586938, "count": 25 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.851298049599998e-06, "min": 5.851298049599998e-06, "max": 0.0002922912025696, "count": 25 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.340519219839999e-05, "min": 2.340519219839999e-05, "max": 0.0014086560304479997, "count": 25 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10195040000000002, "min": 0.10195040000000002, "max": 0.1974304, "count": 25 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4078016000000001, "min": 0.4078016000000001, "max": 0.9695520000000001, "count": 25 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00010732495999999999, "min": 0.00010732495999999999, "max": 0.00487177696, "count": 25 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00042929983999999996, "min": 0.00042929983999999996, "max": 0.023480644800000002, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.954545454545453, "min": 2.8484848484848486, "max": 26.4, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1142.0, "min": 94.0, "max": 1452.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.954545454545453, "min": 2.8484848484848486, "max": 26.4, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1142.0, "min": 94.0, "max": 1452.0, "count": 25 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1772026748", "python_version": "3.10.9 (main, Jan 11 2023, 15:21:40) [GCC 11.2.0]", "command_line_arguments": "/kaggle/working/ml-agents/ml-agents/mlagents/trainers/learn.py /kaggle/working/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --resume --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1772027273" }, "total": 524.843204129, "count": 1, "self": 0.2786323700000821, "children": { "run_training.setup": { "total": 0.02138173299999835, "count": 1, "self": 0.02138173299999835 }, "TrainerController.start_learning": { "total": 524.5431900259999, "count": 1, "self": 0.6514209069947583, "children": { "TrainerController._reset_env": { "total": 2.0983625160000656, "count": 1, "self": 2.0983625160000656 }, "TrainerController.advance": { "total": 521.714883710005, "count": 22596, "self": 0.29943081999488186, "children": { "env_step": { "total": 521.4154528900101, "count": 22596, "self": 336.7753636960008, "children": { "SubprocessEnvManager._take_step": { "total": 184.35177250800677, "count": 22596, "self": 1.5921022360280404, "children": { "TorchPolicy.evaluate": { "total": 182.75967027197873, "count": 22596, "self": 182.75967027197873 } } }, "workers": { "total": 0.28831668600253124, "count": 22596, "self": 0.0, "children": { "worker_root": { "total": 523.4458701529994, "count": 22596, "is_parallel": true, "self": 262.9079954829946, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022900650000110545, "count": 1, "is_parallel": true, "self": 0.0007530260000976341, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015370389999134204, "count": 10, "is_parallel": true, "self": 0.0015370389999134204 } } }, "UnityEnvironment.step": { "total": 0.030321350999997776, "count": 1, "is_parallel": true, "self": 0.0003923990000203048, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00025326200000108656, "count": 1, "is_parallel": true, "self": 0.00025326200000108656 }, "communicator.exchange": { "total": 0.028446690000009767, "count": 1, "is_parallel": true, "self": 0.028446690000009767 }, "steps_from_proto": { "total": 0.001228999999966618, "count": 1, "is_parallel": true, "self": 0.0002402349999783837, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009887649999882342, "count": 10, "is_parallel": true, "self": 0.0009887649999882342 } } } } } } }, "UnityEnvironment.step": { "total": 260.53787467000484, "count": 22595, "is_parallel": true, "self": 11.778621210988149, "children": { "UnityEnvironment._generate_step_input": { "total": 6.406724315008546, "count": 22595, "is_parallel": true, "self": 6.406724315008546 }, "communicator.exchange": { "total": 204.68929785800128, "count": 22595, "is_parallel": true, "self": 204.68929785800128 }, "steps_from_proto": { "total": 37.66323128600686, "count": 22595, "is_parallel": true, "self": 6.674950173020989, "children": { "_process_rank_one_or_two_observation": { "total": 30.988281112985874, "count": 225950, "is_parallel": true, "self": 30.988281112985874 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003742380001767742, "count": 1, "self": 0.0003742380001767742, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 517.8904723680122, "count": 537451, "is_parallel": true, "self": 10.924477349966196, "children": { "process_trajectory": { "total": 294.4665337660458, "count": 537451, "is_parallel": true, "self": 293.88906470904556, "children": { "RLTrainer._checkpoint": { "total": 0.5774690570002576, "count": 5, "is_parallel": true, "self": 0.5774690570002576 } } }, "_update_policy": { "total": 212.49946125200017, "count": 112, "is_parallel": true, "self": 42.500768024992226, "children": { "TorchPPOOptimizer.update": { "total": 169.99869322700795, "count": 5709, "is_parallel": true, "self": 169.99869322700795 } } } } } } } } }, "TrainerController._save_models": { "total": 0.07814865499994994, "count": 1, "self": 0.0010259990001486585, "children": { "RLTrainer._checkpoint": { "total": 0.07712265599980128, "count": 1, "self": 0.07712265599980128 } } } } } } }