{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8497298955917358, "min": 0.8497298955917358, "max": 2.854966878890991, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8103.8740234375, "min": 8103.8740234375, "max": 29237.71484375, "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": 13.520991325378418, "min": 0.39857420325279236, "max": 13.520991325378418, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2636.59326171875, "min": 77.32339477539062, "max": 2733.151123046875, "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": 0.051640553846482355, "min": 0.04241921850158784, "max": 0.053829570670980806, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.20656221538592942, "min": 0.16967687400635137, "max": 0.26914785335490404, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18384178029373288, "min": 0.16487218253314495, "max": 0.3027531748016675, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7353671211749315, "min": 0.6594887301325798, "max": 1.5137658740083375, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.885809730600001e-05, "min": 1.885809730600001e-05, "max": 0.0006810580027059999, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 7.543238922400004e-05, "min": 7.543238922400004e-05, "max": 0.0032320400382800005, "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": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014443060000000012, "min": 0.00014443060000000012, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000005, "min": 0.0005777224000000005, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.272727272727273, "min": 3.8863636363636362, "max": 26.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1156.0, "min": 171.0, "max": 1470.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.272727272727273, "min": 3.8863636363636362, "max": 26.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1156.0, "min": 171.0, "max": 1470.0, "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": "1675762017", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1675762481" }, "total": 463.117938063, "count": 1, "self": 0.43254443800014997, "children": { "run_training.setup": { "total": 0.10814192199995887, "count": 1, "self": 0.10814192199995887 }, "TrainerController.start_learning": { "total": 462.5772517029999, "count": 1, "self": 0.5851602189906089, "children": { "TrainerController._reset_env": { "total": 9.800682908999988, "count": 1, "self": 9.800682908999988 }, "TrainerController.advance": { "total": 452.0324936450095, "count": 18202, "self": 0.340239563013256, "children": { "env_step": { "total": 451.6922540819962, "count": 18202, "self": 304.53710158600006, "children": { "SubprocessEnvManager._take_step": { "total": 146.85733423099668, "count": 18202, "self": 1.5128286989973958, "children": { "TorchPolicy.evaluate": { "total": 145.3445055319993, "count": 18202, "self": 33.24556560098506, "children": { "TorchPolicy.sample_actions": { "total": 112.09893993101423, "count": 18202, "self": 112.09893993101423 } } } } }, "workers": { "total": 0.29781826499947783, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 461.0008334580143, "count": 18202, "is_parallel": true, "self": 210.23632525902144, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00547346199994081, "count": 1, "is_parallel": true, "self": 0.003189231999954245, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022842299999865645, "count": 10, "is_parallel": true, "self": 0.0022842299999865645 } } }, "UnityEnvironment.step": { "total": 0.0903859969999985, "count": 1, "is_parallel": true, "self": 0.0005605559999821708, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003563430000212975, "count": 1, "is_parallel": true, "self": 0.0003563430000212975 }, "communicator.exchange": { "total": 0.08776066699999774, "count": 1, "is_parallel": true, "self": 0.08776066699999774 }, "steps_from_proto": { "total": 0.0017084309999972902, "count": 1, "is_parallel": true, "self": 0.0004006379998600096, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013077930001372806, "count": 10, "is_parallel": true, "self": 0.0013077930001372806 } } } } } } }, "UnityEnvironment.step": { "total": 250.76450819899287, "count": 18201, "is_parallel": true, "self": 9.843452205987091, "children": { "UnityEnvironment._generate_step_input": { "total": 5.3098874530036255, "count": 18201, "is_parallel": true, "self": 5.3098874530036255 }, "communicator.exchange": { "total": 203.4100343669944, "count": 18201, "is_parallel": true, "self": 203.4100343669944 }, "steps_from_proto": { "total": 32.201134173007745, "count": 18201, "is_parallel": true, "self": 7.292056571006924, "children": { "_process_rank_one_or_two_observation": { "total": 24.90907760200082, "count": 182010, "is_parallel": true, "self": 24.90907760200082 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012462899985621334, "count": 1, "self": 0.00012462899985621334, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 448.0489555700391, "count": 474258, "is_parallel": true, "self": 11.742948400960586, "children": { "process_trajectory": { "total": 293.2144949620781, "count": 474258, "is_parallel": true, "self": 292.2671304710781, "children": { "RLTrainer._checkpoint": { "total": 0.9473644910000303, "count": 4, "is_parallel": true, "self": 0.9473644910000303 } } }, "_update_policy": { "total": 143.0915122070004, "count": 90, "is_parallel": true, "self": 64.29706306299806, "children": { "TorchPPOOptimizer.update": { "total": 78.79444914400233, "count": 2160, "is_parallel": true, "self": 78.79444914400233 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15879030099995362, "count": 1, "self": 0.0018259639998632338, "children": { "RLTrainer._checkpoint": { "total": 0.15696433700009038, "count": 1, "self": 0.15696433700009038 } } } } } } }