{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.864636242389679, "min": 0.8203649520874023, "max": 1.5189265012741089, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8255.546875, "min": 6549.611328125, "max": 13609.1630859375, "count": 40 }, "SnowballTarget.Step.mean": { "value": 499952.0, "min": 109976.0, "max": 499952.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 499952.0, "min": 109976.0, "max": 499952.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.8157377243042, "min": 9.369784355163574, "max": 13.842137336730957, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2694.06884765625, "min": 627.7755737304688, "max": 2813.323974609375, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 2189.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06334171503291217, "min": 0.04622214240589528, "max": 0.08125960973739697, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25336686013164866, "min": 0.04622214240589528, "max": 0.4062980486869849, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16826069588754694, "min": 0.1534993161757787, "max": 0.23228520873714897, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6730427835501878, "min": 0.21794966142624617, "max": 1.1614260436857449, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.0002258226247258, "min": 0.0002258226247258, "max": 0.00028373760542079997, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0009032904989032, "min": 0.00028373760542079997, "max": 0.001413738028754, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.17527420000000005, "min": 0.17527420000000005, "max": 0.19457919999999998, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.7010968000000002, "min": 0.19457919999999998, "max": 0.9712459999999998, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00376618258, "min": 0.00376618258, "max": 0.00472950208, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.01506473032, "min": 0.00472950208, "max": 0.023565175400000006, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.954545454545453, "min": 19.545454545454547, "max": 27.295454545454547, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1186.0, "min": 215.0, "max": 1495.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.954545454545453, "min": 19.545454545454547, "max": 27.295454545454547, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1186.0, "min": 215.0, "max": 1495.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710409478", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710410323" }, "total": 844.5671383540001, "count": 1, "self": 0.7400595080001722, "children": { "run_training.setup": { "total": 0.05052030699994248, "count": 1, "self": 0.05052030699994248 }, "TrainerController.start_learning": { "total": 843.776558539, "count": 1, "self": 1.0151436209880558, "children": { "TrainerController._reset_env": { "total": 1.9490691789999346, "count": 1, "self": 1.9490691789999346 }, "TrainerController.advance": { "total": 840.653146659012, "count": 36144, "self": 0.47874007598784374, "children": { "env_step": { "total": 840.1744065830242, "count": 36144, "self": 541.7318599540237, "children": { "SubprocessEnvManager._take_step": { "total": 297.92083471402145, "count": 36144, "self": 2.779346825999255, "children": { "TorchPolicy.evaluate": { "total": 295.1414878880222, "count": 36144, "self": 295.1414878880222 } } }, "workers": { "total": 0.5217119149790506, "count": 36143, "self": 0.0, "children": { "worker_root": { "total": 841.5461368460287, "count": 36143, "is_parallel": true, "self": 420.92967734005924, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022644880000370904, "count": 1, "is_parallel": true, "self": 0.0006113540001706497, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016531339998664407, "count": 10, "is_parallel": true, "self": 0.0016531339998664407 } } }, "UnityEnvironment.step": { "total": 0.03597519000004468, "count": 1, "is_parallel": true, "self": 0.0006587450001234174, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003920949999383083, "count": 1, "is_parallel": true, "self": 0.0003920949999383083 }, "communicator.exchange": { "total": 0.032972031999975115, "count": 1, "is_parallel": true, "self": 0.032972031999975115 }, "steps_from_proto": { "total": 0.0019523180000078355, "count": 1, "is_parallel": true, "self": 0.000377611000089928, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015747069999179075, "count": 10, "is_parallel": true, "self": 0.0015747069999179075 } } } } } } }, "UnityEnvironment.step": { "total": 420.6164595059695, "count": 36142, "is_parallel": true, "self": 19.541282589966954, "children": { "UnityEnvironment._generate_step_input": { "total": 10.276662951010394, "count": 36142, "is_parallel": true, "self": 10.276662951010394 }, "communicator.exchange": { "total": 326.67533893098596, "count": 36142, "is_parallel": true, "self": 326.67533893098596 }, "steps_from_proto": { "total": 64.12317503400618, "count": 36142, "is_parallel": true, "self": 11.733031465923773, "children": { "_process_rank_one_or_two_observation": { "total": 52.39014356808241, "count": 361420, "is_parallel": true, "self": 52.39014356808241 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.357400007393153e-05, "count": 1, "self": 4.357400007393153e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 830.2605510590836, "count": 1237395, "is_parallel": true, "self": 26.987675326179442, "children": { "process_trajectory": { "total": 457.0546465729017, "count": 1237395, "is_parallel": true, "self": 455.615314869902, "children": { "RLTrainer._checkpoint": { "total": 1.4393317029996524, "count": 8, "is_parallel": true, "self": 1.4393317029996524 } } }, "_update_policy": { "total": 346.21822916000247, "count": 180, "is_parallel": true, "self": 98.40025826000647, "children": { "TorchPPOOptimizer.update": { "total": 247.817970899996, "count": 9177, "is_parallel": true, "self": 247.817970899996 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15915550599993367, "count": 1, "self": 0.0023052929998357286, "children": { "RLTrainer._checkpoint": { "total": 0.15685021300009794, "count": 1, "self": 0.15685021300009794 } } } } } } }