{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.402003526687622, "min": 1.402003526687622, "max": 1.4235150814056396, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69692.1953125, "min": 68501.4453125, "max": 77261.5078125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 106.2547770700637, "min": 85.52961672473867, "max": 380.7651515151515, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50046.0, "min": 48989.0, "max": 50261.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999778.0, "min": 49831.0, "max": 1999778.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999778.0, "min": 49831.0, "max": 1999778.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.336700916290283, "min": -0.03799854964017868, "max": 2.420351505279541, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1100.586181640625, "min": -4.977809906005859, "max": 1359.320068359375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.530277326861258, "min": 1.7705591807838614, "max": 3.9192370868864512, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1662.7606209516525, "min": 231.94325268268585, "max": 2201.5442913770676, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.530277326861258, "min": 1.7705591807838614, "max": 3.9192370868864512, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1662.7606209516525, "min": 231.94325268268585, "max": 2201.5442913770676, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017498455344078442, "min": 0.013429122308419514, "max": 0.02070954283588738, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.034996910688156885, "min": 0.026858244616839028, "max": 0.05752095837960951, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04404068787892659, "min": 0.024671760077277817, "max": 0.05993577173600595, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08808137575785319, "min": 0.049343520154555634, "max": 0.1731555551290512, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.63059845650001e-06, "min": 4.63059845650001e-06, "max": 0.00029532157655947494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.26119691300002e-06, "min": 9.26119691300002e-06, "max": 0.0008441206686264497, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10154350000000001, "min": 0.10154350000000001, "max": 0.19844052500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20308700000000002, "min": 0.20308700000000002, "max": 0.5813735500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.702065000000018e-05, "min": 8.702065000000018e-05, "max": 0.0049221821975000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017404130000000037, "min": 0.00017404130000000037, "max": 0.014070540145000001, "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": "1680781569", "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": "0.31.0.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": "1680784061" }, "total": 2491.636011404, "count": 1, "self": 0.4389899850002621, "children": { "run_training.setup": { "total": 0.11960203500001398, "count": 1, "self": 0.11960203500001398 }, "TrainerController.start_learning": { "total": 2491.0774193839998, "count": 1, "self": 4.6508671290757775, "children": { "TrainerController._reset_env": { "total": 4.501188755999976, "count": 1, "self": 4.501188755999976 }, "TrainerController.advance": { "total": 2481.791092759924, "count": 231727, "self": 4.796878434859536, "children": { "env_step": { "total": 1953.0167671010743, "count": 231727, "self": 1655.2316312090786, "children": { "SubprocessEnvManager._take_step": { "total": 294.66283759002175, "count": 231727, "self": 17.70253434191102, "children": { "TorchPolicy.evaluate": { "total": 276.96030324811073, "count": 223042, "self": 276.96030324811073 } } }, "workers": { "total": 3.122298301973899, "count": 231727, "self": 0.0, "children": { "worker_root": { "total": 2482.397707393125, "count": 231727, "is_parallel": true, "self": 1126.957464741105, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009388929999545326, "count": 1, "is_parallel": true, "self": 0.00026525300000912466, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006736399999454079, "count": 2, "is_parallel": true, "self": 0.0006736399999454079 } } }, "UnityEnvironment.step": { "total": 0.07978955200002247, "count": 1, "is_parallel": true, "self": 0.0003221830000939008, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002134049999540366, "count": 1, "is_parallel": true, "self": 0.0002134049999540366 }, "communicator.exchange": { "total": 0.0785295119999887, "count": 1, "is_parallel": true, "self": 0.0785295119999887 }, "steps_from_proto": { "total": 0.0007244519999858312, "count": 1, "is_parallel": true, "self": 0.00020391699996480384, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005205350000210274, "count": 2, "is_parallel": true, "self": 0.0005205350000210274 } } } } } } }, "UnityEnvironment.step": { "total": 1355.44024265202, "count": 231726, "is_parallel": true, "self": 40.041921258037746, "children": { "UnityEnvironment._generate_step_input": { "total": 83.47655306998695, "count": 231726, "is_parallel": true, "self": 83.47655306998695 }, "communicator.exchange": { "total": 1137.5264727130032, "count": 231726, "is_parallel": true, "self": 1137.5264727130032 }, "steps_from_proto": { "total": 94.39529561099226, "count": 231726, "is_parallel": true, "self": 35.45729636103664, "children": { "_process_rank_one_or_two_observation": { "total": 58.937999249955624, "count": 463452, "is_parallel": true, "self": 58.937999249955624 } } } } } } } } } } }, "trainer_advance": { "total": 523.9774472239905, "count": 231727, "self": 7.278057776078867, "children": { "process_trajectory": { "total": 135.53127448690952, "count": 231727, "self": 134.22150154191036, "children": { "RLTrainer._checkpoint": { "total": 1.3097729449991675, "count": 10, "self": 1.3097729449991675 } } }, "_update_policy": { "total": 381.16811496100206, "count": 96, "self": 320.88931636999513, "children": { "TorchPPOOptimizer.update": { "total": 60.27879859100693, "count": 2880, "self": 60.27879859100693 } } } } } } }, "trainer_threads": { "total": 9.659997886046767e-07, "count": 1, "self": 9.659997886046767e-07 }, "TrainerController._save_models": { "total": 0.13426977300014187, "count": 1, "self": 0.002718404000006558, "children": { "RLTrainer._checkpoint": { "total": 0.1315513690001353, "count": 1, "self": 0.1315513690001353 } } } } } } }