{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1321903467178345, "min": 1.1321903467178345, "max": 2.873920440673828, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10872.423828125, "min": 10872.423828125, "max": 29431.8203125, "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": 12.436102867126465, "min": 0.45559248328208923, "max": 12.436102867126465, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2425.0400390625, "min": 88.38494110107422, "max": 2497.45263671875, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06429133673744075, "min": 0.06429133673744075, "max": 0.07345170655963895, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.257165346949763, "min": 0.257165346949763, "max": 0.3648258062283846, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20680761183885968, "min": 0.10510232823663482, "max": 0.27600525378012186, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8272304473554387, "min": 0.42040931294653927, "max": 1.3800262689006093, "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": 25.363636363636363, "min": 3.1363636363636362, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1116.0, "min": 138.0, "max": 1355.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.363636363636363, "min": 3.1363636363636362, "max": 25.363636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1116.0, "min": 138.0, "max": 1355.0, "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": "1695331264", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1695331828" }, "total": 563.335585581, "count": 1, "self": 0.8869743089999247, "children": { "run_training.setup": { "total": 0.07341583400000218, "count": 1, "self": 0.07341583400000218 }, "TrainerController.start_learning": { "total": 562.3751954380001, "count": 1, "self": 0.7276764309995087, "children": { "TrainerController._reset_env": { "total": 4.314881501999935, "count": 1, "self": 4.314881501999935 }, "TrainerController.advance": { "total": 557.0009233960005, "count": 18213, "self": 0.3981985970002597, "children": { "env_step": { "total": 556.6027247990003, "count": 18213, "self": 407.93795377498463, "children": { "SubprocessEnvManager._take_step": { "total": 148.298126798015, "count": 18213, "self": 2.29144132401791, "children": { "TorchPolicy.evaluate": { "total": 146.0066854739971, "count": 18213, "self": 146.0066854739971 } } }, "workers": { "total": 0.3666442260006306, "count": 18213, "self": 0.0, "children": { "worker_root": { "total": 560.0245748469985, "count": 18213, "is_parallel": true, "self": 257.94107450198874, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006042525999987447, "count": 1, "is_parallel": true, "self": 0.004329981000068983, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017125449999184639, "count": 10, "is_parallel": true, "self": 0.0017125449999184639 } } }, "UnityEnvironment.step": { "total": 0.04576094699996247, "count": 1, "is_parallel": true, "self": 0.0005194730000539494, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000602358000037384, "count": 1, "is_parallel": true, "self": 0.000602358000037384 }, "communicator.exchange": { "total": 0.041051537999919674, "count": 1, "is_parallel": true, "self": 0.041051537999919674 }, "steps_from_proto": { "total": 0.0035875779999514634, "count": 1, "is_parallel": true, "self": 0.000461780999671646, "children": { "_process_rank_one_or_two_observation": { "total": 0.0031257970002798174, "count": 10, "is_parallel": true, "self": 0.0031257970002798174 } } } } } } }, "UnityEnvironment.step": { "total": 302.0835003450097, "count": 18212, "is_parallel": true, "self": 12.230056430024888, "children": { "UnityEnvironment._generate_step_input": { "total": 6.234582470983696, "count": 18212, "is_parallel": true, "self": 6.234582470983696 }, "communicator.exchange": { "total": 239.2423680279992, "count": 18212, "is_parallel": true, "self": 239.2423680279992 }, "steps_from_proto": { "total": 44.37649341600195, "count": 18212, "is_parallel": true, "self": 8.751798726948323, "children": { "_process_rank_one_or_two_observation": { "total": 35.62469468905363, "count": 182120, "is_parallel": true, "self": 35.62469468905363 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001961150001079659, "count": 1, "self": 0.0001961150001079659, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 552.297722449933, "count": 529372, "is_parallel": true, "self": 13.296027070877471, "children": { "process_trajectory": { "total": 305.4635409730554, "count": 529372, "is_parallel": true, "self": 304.3317492590554, "children": { "RLTrainer._checkpoint": { "total": 1.1317917139999736, "count": 4, "is_parallel": true, "self": 1.1317917139999736 } } }, "_update_policy": { "total": 233.5381544060001, "count": 90, "is_parallel": true, "self": 93.90035019499669, "children": { "TorchPPOOptimizer.update": { "total": 139.6378042110034, "count": 4587, "is_parallel": true, "self": 139.6378042110034 } } } } } } } } }, "TrainerController._save_models": { "total": 0.33151799400002346, "count": 1, "self": 0.001615313000002061, "children": { "RLTrainer._checkpoint": { "total": 0.3299026810000214, "count": 1, "self": 0.3299026810000214 } } } } } } }