{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4067562818527222, "min": 1.4067562818527222, "max": 1.4269779920578003, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70049.4296875, "min": 67781.3359375, "max": 79158.0, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 79.5426731078905, "min": 79.5426731078905, "max": 417.06666666666666, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49396.0, "min": 48716.0, "max": 50253.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999961.0, "min": 49551.0, "max": 1999961.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999961.0, "min": 49551.0, "max": 1999961.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.423034191131592, "min": 0.06623976677656174, "max": 2.4911136627197266, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1504.7042236328125, "min": 7.882532119750977, "max": 1538.2835693359375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7695929401354706, "min": 1.973298088843081, "max": 3.9703760486382706, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2340.917215824127, "min": 234.82247257232666, "max": 2376.1497153043747, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7695929401354706, "min": 1.973298088843081, "max": 3.9703760486382706, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2340.917215824127, "min": 234.82247257232666, "max": 2376.1497153043747, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016664700675998272, "min": 0.01374194950913079, "max": 0.019167340830123673, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04999410202799481, "min": 0.02748389901826158, "max": 0.0543433472320127, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06250082370307711, "min": 0.021875247824937105, "max": 0.06608006426443655, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18750247110923132, "min": 0.04375049564987421, "max": 0.19566542444129786, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4709988430333316e-06, "min": 3.4709988430333316e-06, "max": 0.00029534835155055003, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0412996529099995e-05, "min": 1.0412996529099995e-05, "max": 0.0008438616187127997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10115696666666668, "min": 0.10115696666666668, "max": 0.19844945000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30347090000000004, "min": 0.20744595, "max": 0.5812872000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.773263666666666e-05, "min": 6.773263666666666e-05, "max": 0.004922627555, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020319790999999998, "min": 0.00020319790999999998, "max": 0.014066231279999997, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1690904402", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1690907019" }, "total": 2617.232013147, "count": 1, "self": 0.4975867170001038, "children": { "run_training.setup": { "total": 0.03804440600004, "count": 1, "self": 0.03804440600004 }, "TrainerController.start_learning": { "total": 2616.696382024, "count": 1, "self": 4.968639606009674, "children": { "TrainerController._reset_env": { "total": 7.255112323999924, "count": 1, "self": 7.255112323999924 }, "TrainerController.advance": { "total": 2604.3489495029908, "count": 232373, "self": 4.854882993825413, "children": { "env_step": { "total": 2010.7870737520857, "count": 232373, "self": 1702.6170865949603, "children": { "SubprocessEnvManager._take_step": { "total": 305.0833857310614, "count": 232373, "self": 17.791437039111088, "children": { "TorchPolicy.evaluate": { "total": 287.2919486919503, "count": 222929, "self": 287.2919486919503 } } }, "workers": { "total": 3.0866014260640213, "count": 232373, "self": 0.0, "children": { "worker_root": { "total": 2608.4308732749696, "count": 232373, "is_parallel": true, "self": 1216.330614014982, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010261250000667133, "count": 1, "is_parallel": true, "self": 0.0002700090001326316, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007561159999340816, "count": 2, "is_parallel": true, "self": 0.0007561159999340816 } } }, "UnityEnvironment.step": { "total": 0.05325365099997725, "count": 1, "is_parallel": true, "self": 0.00035362799997074035, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024855499998466257, "count": 1, "is_parallel": true, "self": 0.00024855499998466257 }, "communicator.exchange": { "total": 0.051903831000004175, "count": 1, "is_parallel": true, "self": 0.051903831000004175 }, "steps_from_proto": { "total": 0.0007476370000176757, "count": 1, "is_parallel": true, "self": 0.00021489199991719943, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005327450001004763, "count": 2, "is_parallel": true, "self": 0.0005327450001004763 } } } } } } }, "UnityEnvironment.step": { "total": 1392.1002592599875, "count": 232372, "is_parallel": true, "self": 42.92526972093356, "children": { "UnityEnvironment._generate_step_input": { "total": 87.09691062219042, "count": 232372, "is_parallel": true, "self": 87.09691062219042 }, "communicator.exchange": { "total": 1159.7058963969494, "count": 232372, "is_parallel": true, "self": 1159.7058963969494 }, "steps_from_proto": { "total": 102.37218251991408, "count": 232372, "is_parallel": true, "self": 36.8167333519458, "children": { "_process_rank_one_or_two_observation": { "total": 65.55544916796828, "count": 464744, "is_parallel": true, "self": 65.55544916796828 } } } } } } } } } } }, "trainer_advance": { "total": 588.7069927570794, "count": 232373, "self": 6.973226612099552, "children": { "process_trajectory": { "total": 147.35125599097842, "count": 232373, "self": 145.94127094497844, "children": { "RLTrainer._checkpoint": { "total": 1.4099850459999743, "count": 10, "self": 1.4099850459999743 } } }, "_update_policy": { "total": 434.38251015400147, "count": 97, "self": 371.5012834260024, "children": { "TorchPPOOptimizer.update": { "total": 62.88122672799909, "count": 2910, "self": 62.88122672799909 } } } } } } }, "trainer_threads": { "total": 8.829997568682302e-07, "count": 1, "self": 8.829997568682302e-07 }, "TrainerController._save_models": { "total": 0.12367970799959949, "count": 1, "self": 0.0023990459994820412, "children": { "RLTrainer._checkpoint": { "total": 0.12128066200011745, "count": 1, "self": 0.12128066200011745 } } } } } } }