{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4033162593841553, "min": 1.4033162593841553, "max": 1.4291839599609375, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70823.96875, "min": 69246.578125, "max": 77808.328125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 103.6213389121339, "min": 80.23414634146341, "max": 403.5725806451613, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49531.0, "min": 48886.0, "max": 50247.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999931.0, "min": 49788.0, "max": 1999931.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999931.0, "min": 49788.0, "max": 1999931.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.383114814758301, "min": 0.039106469601392746, "max": 2.4554741382598877, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1139.12890625, "min": 4.81009578704834, "max": 1479.4493408203125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6732675022909334, "min": 1.6868791743749525, "max": 3.918494724779388, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1755.821866095066, "min": 207.48613844811916, "max": 2266.3204256892204, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6732675022909334, "min": 1.6868791743749525, "max": 3.918494724779388, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1755.821866095066, "min": 207.48613844811916, "max": 2266.3204256892204, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018067041301077957, "min": 0.013448072352427214, "max": 0.021407501588449424, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.054201123903233867, "min": 0.02689614470485443, "max": 0.05600913358503021, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.048701976529426046, "min": 0.023229338725407916, "max": 0.06938012138836913, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14610592958827814, "min": 0.04645867745081583, "max": 0.2081403641651074, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4058488647499967e-06, "min": 3.4058488647499967e-06, "max": 0.00029535330154889993, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.021754659424999e-05, "min": 1.021754659424999e-05, "max": 0.00084428536857155, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10113524999999997, "min": 0.10113524999999997, "max": 0.19845110000000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034057499999999, "min": 0.20741394999999996, "max": 0.58142845, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.664897499999996e-05, "min": 6.664897499999996e-05, "max": 0.004922709889999998, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019994692499999988, "min": 0.00019994692499999988, "max": 0.014073279655, "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": "1671774762", "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": "1671776988" }, "total": 2225.984653452, "count": 1, "self": 0.39509331499994005, "children": { "run_training.setup": { "total": 0.1021809830000393, "count": 1, "self": 0.1021809830000393 }, "TrainerController.start_learning": { "total": 2225.4873791540003, "count": 1, "self": 3.8631977839108913, "children": { "TrainerController._reset_env": { "total": 7.788320384000031, "count": 1, "self": 7.788320384000031 }, "TrainerController.advance": { "total": 2213.722803778089, "count": 232236, "self": 3.948941850032952, "children": { "env_step": { "total": 1745.5287680240351, "count": 232236, "self": 1463.9942648122865, "children": { "SubprocessEnvManager._take_step": { "total": 279.011508031871, "count": 232236, "self": 14.445469112956971, "children": { "TorchPolicy.evaluate": { "total": 264.56603891891405, "count": 223039, "self": 66.16494180789459, "children": { "TorchPolicy.sample_actions": { "total": 198.40109711101945, "count": 223039, "self": 198.40109711101945 } } } } }, "workers": { "total": 2.5229951798777392, "count": 232236, "self": 0.0, "children": { "worker_root": { "total": 2217.354980584956, "count": 232236, "is_parallel": true, "self": 1014.5171932018598, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020557279999593447, "count": 1, "is_parallel": true, "self": 0.0003223770000886361, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017333509998707086, "count": 2, "is_parallel": true, "self": 0.0017333509998707086 } } }, "UnityEnvironment.step": { "total": 0.027148061000048074, "count": 1, "is_parallel": true, "self": 0.00029159700000036537, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016882699992493144, "count": 1, "is_parallel": true, "self": 0.00016882699992493144 }, "communicator.exchange": { "total": 0.025987855000039417, "count": 1, "is_parallel": true, "self": 0.025987855000039417 }, "steps_from_proto": { "total": 0.0006997820000833599, "count": 1, "is_parallel": true, "self": 0.00024159700012660323, "children": { "_process_rank_one_or_two_observation": { "total": 0.00045818499995675666, "count": 2, "is_parallel": true, "self": 0.00045818499995675666 } } } } } } }, "UnityEnvironment.step": { "total": 1202.8377873830964, "count": 232235, "is_parallel": true, "self": 34.47277394817911, "children": { "UnityEnvironment._generate_step_input": { "total": 77.96692821689328, "count": 232235, "is_parallel": true, "self": 77.96692821689328 }, "communicator.exchange": { "total": 995.8075172630678, "count": 232235, "is_parallel": true, "self": 995.8075172630678 }, "steps_from_proto": { "total": 94.59056795495621, "count": 232235, "is_parallel": true, "self": 40.6131053879551, "children": { "_process_rank_one_or_two_observation": { "total": 53.97746256700111, "count": 464470, "is_parallel": true, "self": 53.97746256700111 } } } } } } } } } } }, "trainer_advance": { "total": 464.24509390402125, "count": 232236, "self": 5.945064607894096, "children": { "process_trajectory": { "total": 148.45224846212875, "count": 232236, "self": 147.2895266071281, "children": { "RLTrainer._checkpoint": { "total": 1.1627218550006546, "count": 10, "self": 1.1627218550006546 } } }, "_update_policy": { "total": 309.8477808339984, "count": 97, "self": 257.2678437480115, "children": { "TorchPPOOptimizer.update": { "total": 52.5799370859869, "count": 2910, "self": 52.5799370859869 } } } } } } }, "trainer_threads": { "total": 8.699998943484388e-07, "count": 1, "self": 8.699998943484388e-07 }, "TrainerController._save_models": { "total": 0.11305633800020587, "count": 1, "self": 0.002108389000113675, "children": { "RLTrainer._checkpoint": { "total": 0.1109479490000922, "count": 1, "self": 0.1109479490000922 } } } } } } }