{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7058573961257935, "min": 0.6962710022926331, "max": 2.8717200756073, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6708.46875, "min": 6708.46875, "max": 29314.51953125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.004365921020508, "min": 0.3601365089416504, "max": 13.09340763092041, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2535.851318359375, "min": 69.86648559570312, "max": 2671.05517578125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06748398164893611, "min": 0.0613571488069925, "max": 0.0780710944570327, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26993592659574445, "min": 0.24542859522797, "max": 0.3688837748132738, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1976233778484896, "min": 0.11368195293014687, "max": 0.2772987040818906, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7904935113939584, "min": 0.45472781172058746, "max": 1.335435670380499, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.931818181818183, "min": 3.3636363636363638, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1097.0, "min": 148.0, "max": 1423.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.931818181818183, "min": 3.3636363636363638, "max": 25.931818181818183, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1097.0, "min": 148.0, "max": 1423.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1783585746", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1783586204" }, "total": 458.20221096600017, "count": 1, "self": 0.4841248670003324, "children": { "run_training.setup": { "total": 0.02815495799995915, "count": 1, "self": 0.02815495799995915 }, "TrainerController.start_learning": { "total": 457.6899311409999, "count": 1, "self": 0.3863583500068444, "children": { "TrainerController._reset_env": { "total": 3.797366659999966, "count": 1, "self": 3.797366659999966 }, "TrainerController.advance": { "total": 453.42590687599306, "count": 18192, "self": 0.41398964699510543, "children": { "env_step": { "total": 333.98233891199743, "count": 18192, "self": 262.3796814369704, "children": { "SubprocessEnvManager._take_step": { "total": 71.36284980201913, "count": 18192, "self": 1.2832686460169498, "children": { "TorchPolicy.evaluate": { "total": 70.07958115600218, "count": 18192, "self": 70.07958115600218 } } }, "workers": { "total": 0.23980767300793104, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 455.8951945269956, "count": 18192, "is_parallel": true, "self": 225.3073128009887, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007640672999968956, "count": 1, "is_parallel": true, "self": 0.0041886089998115494, "children": { "_process_rank_one_or_two_observation": { "total": 0.0034520640001574066, "count": 10, "is_parallel": true, "self": 0.0034520640001574066 } } }, "UnityEnvironment.step": { "total": 0.04857202600010169, "count": 1, "is_parallel": true, "self": 0.000620173000243085, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044418799996037706, "count": 1, "is_parallel": true, "self": 0.00044418799996037706 }, "communicator.exchange": { "total": 0.04524342999991404, "count": 1, "is_parallel": true, "self": 0.04524342999991404 }, "steps_from_proto": { "total": 0.0022642349999841827, "count": 1, "is_parallel": true, "self": 0.00036811600000419276, "children": { "_process_rank_one_or_two_observation": { "total": 0.00189611899997999, "count": 10, "is_parallel": true, "self": 0.00189611899997999 } } } } } } }, "UnityEnvironment.step": { "total": 230.5878817260069, "count": 18191, "is_parallel": true, "self": 10.556145242002799, "children": { "UnityEnvironment._generate_step_input": { "total": 5.600564963999773, "count": 18191, "is_parallel": true, "self": 5.600564963999773 }, "communicator.exchange": { "total": 176.78119094600413, "count": 18191, "is_parallel": true, "self": 176.78119094600413 }, "steps_from_proto": { "total": 37.64998057400021, "count": 18191, "is_parallel": true, "self": 6.723139694025463, "children": { "_process_rank_one_or_two_observation": { "total": 30.926840879974748, "count": 181910, "is_parallel": true, "self": 30.926840879974748 } } } } } } } } } } }, "trainer_advance": { "total": 119.02957831700053, "count": 18192, "self": 0.4494255679953767, "children": { "process_trajectory": { "total": 24.415754885005867, "count": 18192, "self": 23.958456762005767, "children": { "RLTrainer._checkpoint": { "total": 0.45729812300010053, "count": 4, "self": 0.45729812300010053 } } }, "_update_policy": { "total": 94.16439786399928, "count": 90, "self": 38.35871001200337, "children": { "TorchPPOOptimizer.update": { "total": 55.80568785199591, "count": 4587, "self": 55.80568785199591 } } } } } } }, "trainer_threads": { "total": 8.279998837679159e-07, "count": 1, "self": 8.279998837679159e-07 }, "TrainerController._save_models": { "total": 0.08029842700011613, "count": 1, "self": 0.0008115410000755219, "children": { "RLTrainer._checkpoint": { "total": 0.07948688600004061, "count": 1, "self": 0.07948688600004061 } } } } } } }