{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3994596004486084, "min": 1.3994545936584473, "max": 1.4262529611587524, "count": 80 }, "Huggy.Policy.Entropy.sum": { "value": 69091.3203125, "min": 67996.140625, "max": 78473.7578125, "count": 80 }, "Huggy.Environment.EpisodeLength.mean": { "value": 106.77516059957173, "min": 96.36346153846154, "max": 409.1869918699187, "count": 80 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49864.0, "min": 48946.0, "max": 50330.0, "count": 80 }, "Huggy.Step.mean": { "value": 1999722.0, "min": 49830.0, "max": 1999722.0, "count": 80 }, "Huggy.Step.sum": { "value": 1999722.0, "min": 49830.0, "max": 1999722.0, "count": 80 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3844900131225586, "min": -0.03266797214746475, "max": 2.4043564796447754, "count": 80 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1113.556884765625, "min": -3.985492467880249, "max": 1231.5784912109375, "count": 80 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.737995296014708, "min": 1.8705982751533634, "max": 3.877358000770754, "count": 80 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1745.6438032388687, "min": 228.21298956871033, "max": 1956.4618628025055, "count": 80 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.737995296014708, "min": 1.8705982751533634, "max": 3.877358000770754, "count": 80 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1745.6438032388687, "min": 228.21298956871033, "max": 1956.4618628025055, "count": 80 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01566715299385477, "min": 0.013041166348739353, "max": 0.020335866907973673, "count": 80 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.047001458981564305, "min": 0.026082332697478706, "max": 0.061007600723921016, "count": 80 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04968909236292044, "min": 0.022963962393502395, "max": 0.06116636854906877, "count": 80 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14906727708876133, "min": 0.04592792478700479, "max": 0.17234344196816284, "count": 80 }, "Huggy.Policy.LearningRate.mean": { "value": 3.2214989261999965e-06, "min": 3.2214989261999965e-06, "max": 0.00029538780153739997, "count": 80 }, "Huggy.Policy.LearningRate.sum": { "value": 9.66449677859999e-06, "min": 9.66449677859999e-06, "max": 0.0008442991685669499, "count": 80 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10107379999999998, "min": 0.10107379999999998, "max": 0.19846260000000002, "count": 80 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3032213999999999, "min": 0.20728235000000006, "max": 0.5814330499999999, "count": 80 }, "Huggy.Policy.Beta.mean": { "value": 6.358261999999995e-05, "min": 6.358261999999995e-05, "max": 0.004923283740000001, "count": 80 }, "Huggy.Policy.Beta.sum": { "value": 0.00019074785999999985, "min": 0.00019074785999999985, "max": 0.014073509195, "count": 80 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 80 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 80 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678939218", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678943950" }, "total": 4732.310812225, "count": 1, "self": 1.0026878099997703, "children": { "run_training.setup": { "total": 0.5144782639999903, "count": 1, "self": 0.5144782639999903 }, "TrainerController.start_learning": { "total": 4730.793646151, "count": 1, "self": 8.411695414995847, "children": { "TrainerController._reset_env": { "total": 10.151639448999958, "count": 1, "self": 10.151639448999958 }, "TrainerController.advance": { "total": 4712.008031354004, "count": 231051, "self": 9.035363735507417, "children": { "env_step": { "total": 2925.9286947217597, "count": 231051, "self": 2444.3194892617666, "children": { "SubprocessEnvManager._take_step": { "total": 476.03524205591293, "count": 231051, "self": 32.38727056670814, "children": { "TorchPolicy.evaluate": { "total": 443.6479714892048, "count": 222948, "self": 443.6479714892048 } } }, "workers": { "total": 5.573963404080132, "count": 231051, "self": 0.0, "children": { "worker_root": { "total": 4715.482850130969, "count": 231051, "is_parallel": true, "self": 2769.7048107981645, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014482980000138923, "count": 1, "is_parallel": true, "self": 0.00039525899978798407, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010530390002259082, "count": 2, "is_parallel": true, "self": 0.0010530390002259082 } } }, "UnityEnvironment.step": { "total": 0.03693333900014295, "count": 1, "is_parallel": true, "self": 0.0003643350003130763, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022015299987288017, "count": 1, "is_parallel": true, "self": 0.00022015299987288017 }, "communicator.exchange": { "total": 0.03551187099992603, "count": 1, "is_parallel": true, "self": 0.03551187099992603 }, "steps_from_proto": { "total": 0.0008369800000309624, "count": 1, "is_parallel": true, "self": 0.00025455300010435167, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005824269999266107, "count": 2, "is_parallel": true, "self": 0.0005824269999266107 } } } } } } }, "UnityEnvironment.step": { "total": 1945.7780393328048, "count": 231050, "is_parallel": true, "self": 57.707781384460986, "children": { "UnityEnvironment._generate_step_input": { "total": 89.38376270701065, "count": 231050, "is_parallel": true, "self": 89.38376270701065 }, "communicator.exchange": { "total": 1664.3959521102777, "count": 231050, "is_parallel": true, "self": 1664.3959521102777 }, "steps_from_proto": { "total": 134.29054313105553, "count": 231050, "is_parallel": true, "self": 46.67104611298805, "children": { "_process_rank_one_or_two_observation": { "total": 87.61949701806748, "count": 462100, "is_parallel": true, "self": 87.61949701806748 } } } } } } } } } } }, "trainer_advance": { "total": 1777.0439728967367, "count": 231051, "self": 13.723061976629424, "children": { "process_trajectory": { "total": 246.68300399210398, "count": 231051, "self": 245.13590256310385, "children": { "RLTrainer._checkpoint": { "total": 1.5471014290001222, "count": 10, "self": 1.5471014290001222 } } }, "_update_policy": { "total": 1516.6379069280033, "count": 97, "self": 419.1272872510233, "children": { "TorchPPOOptimizer.update": { "total": 1097.51061967698, "count": 2910, "self": 1097.51061967698 } } } } } } }, "trainer_threads": { "total": 1.446000169380568e-06, "count": 1, "self": 1.446000169380568e-06 }, "TrainerController._save_models": { "total": 0.2222784870000396, "count": 1, "self": 0.0041233039992221165, "children": { "RLTrainer._checkpoint": { "total": 0.2181551830008175, "count": 1, "self": 0.2181551830008175 } } } } } } }