{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.9358608722686768, "min": 1.9358608722686768, "max": 2.8482613563537598, "count": 8 }, "SnowballTarget.Policy.Entropy.sum": { "value": 19931.623046875, "min": 19931.623046875, "max": 29075.05078125, "count": 8 }, "SnowballTarget.Step.mean": { "value": 79968.0, "min": 9952.0, "max": 79968.0, "count": 8 }, "SnowballTarget.Step.sum": { "value": 79968.0, "min": 9952.0, "max": 79968.0, "count": 8 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 7.461071491241455, "min": 0.2932460904121399, "max": 7.461071491241455, "count": 8 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1522.05859375, "min": 56.889739990234375, "max": 1522.05859375, "count": 8 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06488326634965179, "min": 0.06308913043809725, "max": 0.073130420345942, "count": 8 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.32441633174825896, "min": 0.27174333068450873, "max": 0.3463972639349545, "count": 8 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.27419328701262385, "min": 0.12139458527363947, "max": 0.293154604148631, "count": 8 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.3709664350631192, "min": 0.4855783410945579, "max": 1.3946799031075308, "count": 8 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.9830093389999996e-05, "min": 1.9830093389999996e-05, "max": 0.00027970500676499996, "count": 8 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 9.915046694999999e-05, "min": 9.915046694999999e-05, "max": 0.0012129000957, "count": 8 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10661000000000001, "min": 0.10661000000000001, "max": 0.19323500000000002, "count": 8 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.53305, "min": 0.47594000000000003, "max": 0.9043000000000001, "count": 8 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0003398390000000001, "min": 0.0003398390000000001, "max": 0.0046624265000000005, "count": 8 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0016991950000000006, "min": 0.0016991950000000006, "max": 0.02022457, "count": 8 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 8 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 8 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 17.145454545454545, "min": 3.340909090909091, "max": 17.145454545454545, "count": 8 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 943.0, "min": 147.0, "max": 943.0, "count": 8 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 17.145454545454545, "min": 3.340909090909091, "max": 17.145454545454545, "count": 8 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 943.0, "min": 147.0, "max": 943.0, "count": 8 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 8 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 8 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1742992964", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742993204" }, "total": 239.80585605699991, "count": 1, "self": 0.9279279909999332, "children": { "run_training.setup": { "total": 0.03956769199999144, "count": 1, "self": 0.03956769199999144 }, "TrainerController.start_learning": { "total": 238.838360374, "count": 1, "self": 0.2520769939985712, "children": { "TrainerController._reset_env": { "total": 3.7963413200000105, "count": 1, "self": 3.7963413200000105 }, "TrainerController.advance": { "total": 234.68782666300137, "count": 7328, "self": 0.26227418099938404, "children": { "env_step": { "total": 167.32215617700479, "count": 7328, "self": 144.2428043570102, "children": { "SubprocessEnvManager._take_step": { "total": 22.92308768499754, "count": 7328, "self": 0.7601262289899751, "children": { "TorchPolicy.evaluate": { "total": 22.162961456007565, "count": 7328, "self": 22.162961456007565 } } }, "workers": { "total": 0.15626413499705905, "count": 7328, "self": 0.0, "children": { "worker_root": { "total": 237.92768148299967, "count": 7328, "is_parallel": true, "self": 111.8503312030025, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008004618999962076, "count": 1, "is_parallel": true, "self": 0.005578962999948089, "children": { "_process_rank_one_or_two_observation": { "total": 0.002425656000013987, "count": 10, "is_parallel": true, "self": 0.002425656000013987 } } }, "UnityEnvironment.step": { "total": 0.05041669100000945, "count": 1, "is_parallel": true, "self": 0.000837118000049486, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000571386000046914, "count": 1, "is_parallel": true, "self": 0.000571386000046914 }, "communicator.exchange": { "total": 0.04665097399993101, "count": 1, "is_parallel": true, "self": 0.04665097399993101 }, "steps_from_proto": { "total": 0.002357212999982039, "count": 1, "is_parallel": true, "self": 0.0004612010002347233, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018960119997473157, "count": 10, "is_parallel": true, "self": 0.0018960119997473157 } } } } } } }, "UnityEnvironment.step": { "total": 126.07735027999718, "count": 7327, "is_parallel": true, "self": 6.346507882003834, "children": { "UnityEnvironment._generate_step_input": { "total": 3.3031995200017263, "count": 7327, "is_parallel": true, "self": 3.3031995200017263 }, "communicator.exchange": { "total": 98.31721397600029, "count": 7327, "is_parallel": true, "self": 98.31721397600029 }, "steps_from_proto": { "total": 18.110428901991327, "count": 7327, "is_parallel": true, "self": 3.355520439002362, "children": { "_process_rank_one_or_two_observation": { "total": 14.754908462988965, "count": 73270, "is_parallel": true, "self": 14.754908462988965 } } } } } } } } } } }, "trainer_advance": { "total": 67.1033963049972, "count": 7328, "self": 0.31217211599368966, "children": { "process_trajectory": { "total": 12.763442678003798, "count": 7328, "self": 12.301210169003639, "children": { "RLTrainer._checkpoint": { "total": 0.46223250900015955, "count": 4, "self": 0.46223250900015955 } } }, "_update_policy": { "total": 54.027781510999716, "count": 36, "self": 21.843356452996204, "children": { "TorchPPOOptimizer.update": { "total": 32.18442505800351, "count": 1833, "self": 32.18442505800351 } } } } } } }, "trainer_threads": { "total": 1.5640000583516667e-06, "count": 1, "self": 1.5640000583516667e-06 }, "TrainerController._save_models": { "total": 0.10211383299997578, "count": 1, "self": 0.0018527319998611347, "children": { "RLTrainer._checkpoint": { "total": 0.10026110100011465, "count": 1, "self": 0.10026110100011465 } } } } } } }