{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4024274349212646, "min": 1.4024274349212646, "max": 1.4265638589859009, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70153.625, "min": 68620.1796875, "max": 77284.828125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.60195758564437, "min": 77.46153846153847, "max": 392.74015748031496, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49409.0, "min": 49096.0, "max": 50433.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999927.0, "min": 49988.0, "max": 1999927.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999927.0, "min": 49988.0, "max": 1999927.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.508275270462036, "min": 0.12733498215675354, "max": 2.508275270462036, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1537.57275390625, "min": 16.044208526611328, "max": 1556.33642578125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9064133249916027, "min": 1.6908568903094245, "max": 3.9869881114224808, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2394.6313682198524, "min": 213.0479681789875, "max": 2467.919152677059, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9064133249916027, "min": 1.6908568903094245, "max": 3.9869881114224808, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2394.6313682198524, "min": 213.0479681789875, "max": 2467.919152677059, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017141430794840238, "min": 0.013304772768363667, "max": 0.019576360335728772, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05142429238452072, "min": 0.026609545536727335, "max": 0.05697070937846244, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05309478297001785, "min": 0.020414066532005865, "max": 0.06050681496659915, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15928434891005355, "min": 0.04082813306401173, "max": 0.17948120025297004, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5693988102333307e-06, "min": 3.5693988102333307e-06, "max": 0.000295276426574525, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0708196430699992e-05, "min": 1.0708196430699992e-05, "max": 0.0008438037187320998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10118976666666667, "min": 0.10118976666666667, "max": 0.19842547499999993, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3035693, "min": 0.2075163, "max": 0.5812679, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.936935666666663e-05, "min": 6.936935666666663e-05, "max": 0.004921431202500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020810806999999986, "min": 0.00020810806999999986, "max": 0.014065268210000002, "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": "1671629782", "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": "1671631961" }, "total": 2178.659919618, "count": 1, "self": 0.3871541320004326, "children": { "run_training.setup": { "total": 0.11421816000000717, "count": 1, "self": 0.11421816000000717 }, "TrainerController.start_learning": { "total": 2178.1585473259997, "count": 1, "self": 3.584698171835498, "children": { "TrainerController._reset_env": { "total": 8.356933104999996, "count": 1, "self": 8.356933104999996 }, "TrainerController.advance": { "total": 2166.104016406164, "count": 233026, "self": 3.832270423119553, "children": { "env_step": { "total": 1699.5573915460309, "count": 233026, "self": 1431.081252985044, "children": { "SubprocessEnvManager._take_step": { "total": 266.0312287159685, "count": 233026, "self": 13.68852785801812, "children": { "TorchPolicy.evaluate": { "total": 252.34270085795038, "count": 222924, "self": 63.39850466797577, "children": { "TorchPolicy.sample_actions": { "total": 188.9441961899746, "count": 222924, "self": 188.9441961899746 } } } } }, "workers": { "total": 2.4449098450181737, "count": 233026, "self": 0.0, "children": { "worker_root": { "total": 2170.42952545696, "count": 233026, "is_parallel": true, "self": 991.3190265461294, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002150382999957401, "count": 1, "is_parallel": true, "self": 0.0003206289999866385, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018297539999707624, "count": 2, "is_parallel": true, "self": 0.0018297539999707624 } } }, "UnityEnvironment.step": { "total": 0.02641098199995895, "count": 1, "is_parallel": true, "self": 0.0003062109998950291, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016923700002280384, "count": 1, "is_parallel": true, "self": 0.00016923700002280384 }, "communicator.exchange": { "total": 0.025235633000022517, "count": 1, "is_parallel": true, "self": 0.025235633000022517 }, "steps_from_proto": { "total": 0.000699901000018599, "count": 1, "is_parallel": true, "self": 0.00022644900002433133, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004734519999942677, "count": 2, "is_parallel": true, "self": 0.0004734519999942677 } } } } } } }, "UnityEnvironment.step": { "total": 1179.1104989108308, "count": 233025, "is_parallel": true, "self": 33.967504459721795, "children": { "UnityEnvironment._generate_step_input": { "total": 74.30542899799491, "count": 233025, "is_parallel": true, "self": 74.30542899799491 }, "communicator.exchange": { "total": 980.1383388090777, "count": 233025, "is_parallel": true, "self": 980.1383388090777 }, "steps_from_proto": { "total": 90.6992266440364, "count": 233025, "is_parallel": true, "self": 37.218529018138156, "children": { "_process_rank_one_or_two_observation": { "total": 53.480697625898244, "count": 466050, "is_parallel": true, "self": 53.480697625898244 } } } } } } } } } } }, "trainer_advance": { "total": 462.7143544370137, "count": 233026, "self": 6.037760518985408, "children": { "process_trajectory": { "total": 147.60064143103006, "count": 233026, "self": 146.44513149403036, "children": { "RLTrainer._checkpoint": { "total": 1.1555099369996924, "count": 10, "self": 1.1555099369996924 } } }, "_update_policy": { "total": 309.07595248699823, "count": 97, "self": 256.3538094319913, "children": { "TorchPPOOptimizer.update": { "total": 52.72214305500694, "count": 2910, "self": 52.72214305500694 } } } } } } }, "trainer_threads": { "total": 9.110003702517133e-07, "count": 1, "self": 9.110003702517133e-07 }, "TrainerController._save_models": { "total": 0.11289873199984868, "count": 1, "self": 0.001901040999655379, "children": { "RLTrainer._checkpoint": { "total": 0.1109976910001933, "count": 1, "self": 0.1109976910001933 } } } } } } }