{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4054149389266968, "min": 1.4054149389266968, "max": 1.4284106492996216, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70530.75, "min": 69194.4140625, "max": 76763.234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 82.1523178807947, "min": 81.62148760330578, "max": 410.6639344262295, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49620.0, "min": 48939.0, "max": 50101.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999871.0, "min": 49832.0, "max": 1999871.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999871.0, "min": 49832.0, "max": 1999871.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.438931703567505, "min": 0.0032370223198086023, "max": 2.4800257682800293, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1475.5537109375, "min": 0.39167970418930054, "max": 1475.5537109375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.709846794112655, "min": 1.715446182518951, "max": 3.9455936284127358, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2244.457310438156, "min": 207.5689880847931, "max": 2260.8322855830193, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.709846794112655, "min": 1.715446182518951, "max": 3.9455936284127358, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2244.457310438156, "min": 207.5689880847931, "max": 2260.8322855830193, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016388515260364833, "min": 0.014283688926176789, "max": 0.020347534387838095, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0491655457810945, "min": 0.028567377852353578, "max": 0.054821102791659845, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.060021475454171504, "min": 0.022460032254457474, "max": 0.060021475454171504, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18006442636251452, "min": 0.04492006450891495, "max": 0.18006442636251452, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1500989499999974e-06, "min": 3.1500989499999974e-06, "max": 0.0002953654515448499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.450296849999993e-06, "min": 9.450296849999993e-06, "max": 0.0008441361186213, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10105000000000001, "min": 0.10105000000000001, "max": 0.19845515000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30315000000000003, "min": 0.20722970000000002, "max": 0.5813787000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.239499999999996e-05, "min": 6.239499999999996e-05, "max": 0.004922911985, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018718499999999987, "min": 0.00018718499999999987, "max": 0.014070797130000003, "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": "1690229464", "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": "1690231919" }, "total": 2455.280086517, "count": 1, "self": 0.7300835220003137, "children": { "run_training.setup": { "total": 0.05247113299998318, "count": 1, "self": 0.05247113299998318 }, "TrainerController.start_learning": { "total": 2454.497531862, "count": 1, "self": 4.403187370012802, "children": { "TrainerController._reset_env": { "total": 5.76819392699997, "count": 1, "self": 5.76819392699997 }, "TrainerController.advance": { "total": 2444.1463567369874, "count": 232542, "self": 4.460955657943487, "children": { "env_step": { "total": 1885.0576356229285, "count": 232542, "self": 1592.0210191549452, "children": { "SubprocessEnvManager._take_step": { "total": 290.1389838290252, "count": 232542, "self": 16.245412047993227, "children": { "TorchPolicy.evaluate": { "total": 273.893571781032, "count": 222970, "self": 273.893571781032 } } }, "workers": { "total": 2.8976326389581573, "count": 232542, "self": 0.0, "children": { "worker_root": { "total": 2446.5449558329974, "count": 232542, "is_parallel": true, "self": 1145.6597187409861, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012273140000047533, "count": 1, "is_parallel": true, "self": 0.0003689739999686026, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008583400000361507, "count": 2, "is_parallel": true, "self": 0.0008583400000361507 } } }, "UnityEnvironment.step": { "total": 0.028466074999982993, "count": 1, "is_parallel": true, "self": 0.0003360029999157632, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002158210000402505, "count": 1, "is_parallel": true, "self": 0.0002158210000402505 }, "communicator.exchange": { "total": 0.027197907000015675, "count": 1, "is_parallel": true, "self": 0.027197907000015675 }, "steps_from_proto": { "total": 0.0007163440000113042, "count": 1, "is_parallel": true, "self": 0.00022002500008966308, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004963189999216411, "count": 2, "is_parallel": true, "self": 0.0004963189999216411 } } } } } } }, "UnityEnvironment.step": { "total": 1300.8852370920113, "count": 232541, "is_parallel": true, "self": 39.99522469596195, "children": { "UnityEnvironment._generate_step_input": { "total": 80.4625429600045, "count": 232541, "is_parallel": true, "self": 80.4625429600045 }, "communicator.exchange": { "total": 1084.7957662049964, "count": 232541, "is_parallel": true, "self": 1084.7957662049964 }, "steps_from_proto": { "total": 95.63170323104839, "count": 232541, "is_parallel": true, "self": 34.71776995011453, "children": { "_process_rank_one_or_two_observation": { "total": 60.91393328093386, "count": 465082, "is_parallel": true, "self": 60.91393328093386 } } } } } } } } } } }, "trainer_advance": { "total": 554.6277654561154, "count": 232542, "self": 6.685059009215138, "children": { "process_trajectory": { "total": 138.3218467968996, "count": 232542, "self": 136.95409627289968, "children": { "RLTrainer._checkpoint": { "total": 1.3677505239999164, "count": 10, "self": 1.3677505239999164 } } }, "_update_policy": { "total": 409.6208596500006, "count": 97, "self": 349.9666797089991, "children": { "TorchPPOOptimizer.update": { "total": 59.65417994100153, "count": 2910, "self": 59.65417994100153 } } } } } } }, "trainer_threads": { "total": 1.8639998415892478e-06, "count": 1, "self": 1.8639998415892478e-06 }, "TrainerController._save_models": { "total": 0.17979196399983266, "count": 1, "self": 0.0027320760000293376, "children": { "RLTrainer._checkpoint": { "total": 0.17705988799980332, "count": 1, "self": 0.17705988799980332 } } } } } } }