{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8860312104225159, "min": 0.8860312104225159, "max": 2.8547184467315674, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8469.572265625, "min": 8469.572265625, "max": 29235.171875, "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": 12.401437759399414, "min": 0.43631571531295776, "max": 12.401437759399414, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2418.2802734375, "min": 84.64524841308594, "max": 2469.08642578125, "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": 0.06929926320541804, "min": 0.06106660047896416, "max": 0.07362245074317815, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2771970528216722, "min": 0.2522543780474984, "max": 0.3626175124987711, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20916674607524685, "min": 0.12856522972773138, "max": 0.2808943573166342, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8366669843009874, "min": 0.5142609189109255, "max": 1.404471786583171, "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": 25.15909090909091, "min": 3.5454545454545454, "max": 25.15909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1107.0, "min": 156.0, "max": 1360.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.15909090909091, "min": 3.5454545454545454, "max": 25.15909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1107.0, "min": 156.0, "max": 1360.0, "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": "1686488743", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1686489219" }, "total": 475.712537186, "count": 1, "self": 0.38365829800005713, "children": { "run_training.setup": { "total": 0.04212836400000697, "count": 1, "self": 0.04212836400000697 }, "TrainerController.start_learning": { "total": 475.28675052399996, "count": 1, "self": 0.6000244030034878, "children": { "TrainerController._reset_env": { "total": 4.0133400439999605, "count": 1, "self": 4.0133400439999605 }, "TrainerController.advance": { "total": 470.5411099679965, "count": 18203, "self": 0.2956814329763233, "children": { "env_step": { "total": 470.24542853502015, "count": 18203, "self": 343.2098262260198, "children": { "SubprocessEnvManager._take_step": { "total": 126.74192283399861, "count": 18203, "self": 1.8255496789951735, "children": { "TorchPolicy.evaluate": { "total": 124.91637315500344, "count": 18203, "self": 124.91637315500344 } } }, "workers": { "total": 0.2936794750017384, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 473.58662686099785, "count": 18203, "is_parallel": true, "self": 218.97701059199898, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004993671000022459, "count": 1, "is_parallel": true, "self": 0.0034961370000132774, "children": { "_process_rank_one_or_two_observation": { "total": 0.001497534000009182, "count": 10, "is_parallel": true, "self": 0.001497534000009182 } } }, "UnityEnvironment.step": { "total": 0.0460440100000028, "count": 1, "is_parallel": true, "self": 0.0005654870000171286, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030069799998955205, "count": 1, "is_parallel": true, "self": 0.00030069799998955205 }, "communicator.exchange": { "total": 0.04301984500000344, "count": 1, "is_parallel": true, "self": 0.04301984500000344 }, "steps_from_proto": { "total": 0.0021579799999926763, "count": 1, "is_parallel": true, "self": 0.00037325000005239417, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017847299999402821, "count": 10, "is_parallel": true, "self": 0.0017847299999402821 } } } } } } }, "UnityEnvironment.step": { "total": 254.60961626899888, "count": 18202, "is_parallel": true, "self": 9.950199223993877, "children": { "UnityEnvironment._generate_step_input": { "total": 5.308905314002402, "count": 18202, "is_parallel": true, "self": 5.308905314002402 }, "communicator.exchange": { "total": 205.67245253699713, "count": 18202, "is_parallel": true, "self": 205.67245253699713 }, "steps_from_proto": { "total": 33.67805919400547, "count": 18202, "is_parallel": true, "self": 6.583394628998633, "children": { "_process_rank_one_or_two_observation": { "total": 27.094664565006838, "count": 182020, "is_parallel": true, "self": 27.094664565006838 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012717300000986143, "count": 1, "self": 0.00012717300000986143, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 466.88163048496557, "count": 465441, "is_parallel": true, "self": 10.076395576984055, "children": { "process_trajectory": { "total": 256.432567695982, "count": 465441, "is_parallel": true, "self": 255.20579185698193, "children": { "RLTrainer._checkpoint": { "total": 1.2267758390000836, "count": 4, "is_parallel": true, "self": 1.2267758390000836 } } }, "_update_policy": { "total": 200.3726672119995, "count": 90, "is_parallel": true, "self": 74.59332602600608, "children": { "TorchPPOOptimizer.update": { "total": 125.77934118599342, "count": 4587, "is_parallel": true, "self": 125.77934118599342 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13214893600002142, "count": 1, "self": 0.0008774120000225594, "children": { "RLTrainer._checkpoint": { "total": 0.13127152399999886, "count": 1, "self": 0.13127152399999886 } } } } } } }