{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9426395893096924, "min": 0.9426395893096924, "max": 2.8741087913513184, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9031.4296875, "min": 9031.4296875, "max": 29465.36328125, "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": 12.787432670593262, "min": 0.32414156198501587, "max": 12.787432670593262, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2493.54931640625, "min": 62.883460998535156, "max": 2596.58837890625, "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.Losses.PolicyLoss.mean": { "value": 0.07353624439451331, "min": 0.06412645989164993, "max": 0.07584518285576076, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29414497757805325, "min": 0.2565058395665997, "max": 0.36781436196216577, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17465215954272187, "min": 0.11529006784001145, "max": 0.2974722853624353, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6986086381708875, "min": 0.4611602713600458, "max": 1.4819341474304013, "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.CumulativeReward.mean": { "value": 24.818181818181817, "min": 3.0454545454545454, "max": 25.472727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1092.0, "min": 134.0, "max": 1401.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.818181818181817, "min": 3.0454545454545454, "max": 25.472727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1092.0, "min": 134.0, "max": 1401.0, "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": "1736745290", "python_version": "3.10.11 (main, May 16 2023, 00:28:57) [GCC 11.2.0]", "command_line_arguments": "/home/alex/.conda/envs/hf_ml_agent/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": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1736745545" }, "total": 255.63392241401016, "count": 1, "self": 0.2183188900235109, "children": { "run_training.setup": { "total": 0.012009264988591895, "count": 1, "self": 0.012009264988591895 }, "TrainerController.start_learning": { "total": 255.40359425899806, "count": 1, "self": 0.3924331598391291, "children": { "TrainerController._reset_env": { "total": 1.0430833869904745, "count": 1, "self": 1.0430833869904745 }, "TrainerController.advance": { "total": 253.9239270791586, "count": 18205, "self": 0.18097465721075423, "children": { "env_step": { "total": 253.74295242194785, "count": 18205, "self": 198.70729898713762, "children": { "SubprocessEnvManager._take_step": { "total": 54.83591691820766, "count": 18205, "self": 0.8622380902525038, "children": { "TorchPolicy.evaluate": { "total": 53.973678827955155, "count": 18205, "self": 53.973678827955155 } } }, "workers": { "total": 0.1997365166025702, "count": 18205, "self": 0.0, "children": { "worker_root": { "total": 254.92753896740032, "count": 18205, "is_parallel": true, "self": 117.59007748405566, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00111954499152489, "count": 1, "is_parallel": true, "self": 0.00031676000799052417, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008027849835343659, "count": 10, "is_parallel": true, "self": 0.0008027849835343659 } } }, "UnityEnvironment.step": { "total": 0.019298279017675668, "count": 1, "is_parallel": true, "self": 0.0006107980152592063, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019414001144468784, "count": 1, "is_parallel": true, "self": 0.00019414001144468784 }, "communicator.exchange": { "total": 0.016611561994068325, "count": 1, "is_parallel": true, "self": 0.016611561994068325 }, "steps_from_proto": { "total": 0.0018817789969034493, "count": 1, "is_parallel": true, "self": 0.00030999103910289705, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015717879578005522, "count": 10, "is_parallel": true, "self": 0.0015717879578005522 } } } } } } }, "UnityEnvironment.step": { "total": 137.33746148334467, "count": 18204, "is_parallel": true, "self": 6.437391767278314, "children": { "UnityEnvironment._generate_step_input": { "total": 3.2540848202770576, "count": 18204, "is_parallel": true, "self": 3.2540848202770576 }, "communicator.exchange": { "total": 108.59664281638106, "count": 18204, "is_parallel": true, "self": 108.59664281638106 }, "steps_from_proto": { "total": 19.049342079408234, "count": 18204, "is_parallel": true, "self": 3.5765158791909926, "children": { "_process_rank_one_or_two_observation": { "total": 15.472826200217241, "count": 182040, "is_parallel": true, "self": 15.472826200217241 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011508399620652199, "count": 1, "self": 0.00011508399620652199, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 253.23232276400086, "count": 226403, "is_parallel": true, "self": 2.496510009485064, "children": { "process_trajectory": { "total": 142.82834840059513, "count": 226403, "is_parallel": true, "self": 142.4639571965672, "children": { "RLTrainer._checkpoint": { "total": 0.3643912040279247, "count": 4, "is_parallel": true, "self": 0.3643912040279247 } } }, "_update_policy": { "total": 107.90746435392066, "count": 90, "is_parallel": true, "self": 24.013752358063357, "children": { "TorchPPOOptimizer.update": { "total": 83.8937119958573, "count": 4587, "is_parallel": true, "self": 83.8937119958573 } } } } } } } } }, "TrainerController._save_models": { "total": 0.044035549013642594, "count": 1, "self": 0.0004943800158798695, "children": { "RLTrainer._checkpoint": { "total": 0.043541168997762725, "count": 1, "self": 0.043541168997762725 } } } } } } }