{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4050170183181763, "min": 1.4050170183181763, "max": 1.426651954650879, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70291.59375, "min": 68990.5078125, "max": 76767.703125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 74.4524886877828, "min": 72.83161004431315, "max": 431.48275862068965, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49362.0, "min": 49275.0, "max": 50174.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999934.0, "min": 49418.0, "max": 1999934.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999934.0, "min": 49418.0, "max": 1999934.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.482393741607666, "min": 0.04523396119475365, "max": 2.5163261890411377, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1645.8270263671875, "min": 5.201905727386475, "max": 1652.642333984375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9005745437170405, "min": 2.0109472803447557, "max": 4.0343780570997385, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2586.080922484398, "min": 231.2589372396469, "max": 2589.1793364286423, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9005745437170405, "min": 2.0109472803447557, "max": 4.0343780570997385, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2586.080922484398, "min": 231.2589372396469, "max": 2589.1793364286423, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017136462246546417, "min": 0.013975194874324692, "max": 0.020324418674378345, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.051409386739639254, "min": 0.02864614243929585, "max": 0.05902355649159291, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05940213927792178, "min": 0.021886035241186617, "max": 0.061489281989634034, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17820641783376534, "min": 0.043772070482373235, "max": 0.1822053258617719, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.813348728916668e-06, "min": 3.813348728916668e-06, "max": 0.00029531805156064994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1440046186750004e-05, "min": 1.1440046186750004e-05, "max": 0.0008437927687357499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10127108333333334, "min": 0.10127108333333334, "max": 0.19843934999999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30381325000000003, "min": 0.20767334999999998, "max": 0.5812642499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.342705833333338e-05, "min": 7.342705833333338e-05, "max": 0.004922123565, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022028117500000013, "min": 0.00022028117500000013, "max": 0.014065086075, "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": "1671394844", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.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": "1671397005" }, "total": 2161.241137359, "count": 1, "self": 0.3856737759997486, "children": { "run_training.setup": { "total": 0.10407238400000551, "count": 1, "self": 0.10407238400000551 }, "TrainerController.start_learning": { "total": 2160.751391199, "count": 1, "self": 3.648774548024903, "children": { "TrainerController._reset_env": { "total": 7.524637197000004, "count": 1, "self": 7.524637197000004 }, "TrainerController.advance": { "total": 2149.4611318199745, "count": 233192, "self": 3.8762554740674204, "children": { "env_step": { "total": 1687.9759280688968, "count": 233192, "self": 1418.5031001897878, "children": { "SubprocessEnvManager._take_step": { "total": 266.9928251191177, "count": 233192, "self": 13.74408993898345, "children": { "TorchPolicy.evaluate": { "total": 253.24873518013425, "count": 222912, "self": 63.788968412236045, "children": { "TorchPolicy.sample_actions": { "total": 189.4597667678982, "count": 222912, "self": 189.4597667678982 } } } } }, "workers": { "total": 2.48000275999118, "count": 233192, "self": 0.0, "children": { "worker_root": { "total": 2153.032990063008, "count": 233192, "is_parallel": true, "self": 980.6905790689841, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018505009999785216, "count": 1, "is_parallel": true, "self": 0.00034405799999603914, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015064429999824824, "count": 2, "is_parallel": true, "self": 0.0015064429999824824 } } }, "UnityEnvironment.step": { "total": 0.026080995999961942, "count": 1, "is_parallel": true, "self": 0.00025182499996390106, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019859700000779412, "count": 1, "is_parallel": true, "self": 0.00019859700000779412 }, "communicator.exchange": { "total": 0.024942209000016646, "count": 1, "is_parallel": true, "self": 0.024942209000016646 }, "steps_from_proto": { "total": 0.0006883649999736008, "count": 1, "is_parallel": true, "self": 0.00023129999988213967, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004570650000914611, "count": 2, "is_parallel": true, "self": 0.0004570650000914611 } } } } } } }, "UnityEnvironment.step": { "total": 1172.342410994024, "count": 233191, "is_parallel": true, "self": 34.03595714301514, "children": { "UnityEnvironment._generate_step_input": { "total": 74.89827083195433, "count": 233191, "is_parallel": true, "self": 74.89827083195433 }, "communicator.exchange": { "total": 972.4616251330275, "count": 233191, "is_parallel": true, "self": 972.4616251330275 }, "steps_from_proto": { "total": 90.946557886027, "count": 233191, "is_parallel": true, "self": 37.46099689316998, "children": { "_process_rank_one_or_two_observation": { "total": 53.48556099285702, "count": 466382, "is_parallel": true, "self": 53.48556099285702 } } } } } } } } } } }, "trainer_advance": { "total": 457.60894827701014, "count": 233192, "self": 5.988911645124745, "children": { "process_trajectory": { "total": 147.5534128158858, "count": 233192, "self": 146.41793711388522, "children": { "RLTrainer._checkpoint": { "total": 1.1354757020005763, "count": 10, "self": 1.1354757020005763 } } }, "_update_policy": { "total": 304.0666238159996, "count": 97, "self": 251.89721985501103, "children": { "TorchPPOOptimizer.update": { "total": 52.169403960988575, "count": 2910, "self": 52.169403960988575 } } } } } } }, "trainer_threads": { "total": 8.960000741353724e-07, "count": 1, "self": 8.960000741353724e-07 }, "TrainerController._save_models": { "total": 0.11684673800027667, "count": 1, "self": 0.0028551100003824104, "children": { "RLTrainer._checkpoint": { "total": 0.11399162799989426, "count": 1, "self": 0.11399162799989426 } } } } } } }