{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4008787870407104, "min": 1.4008787870407104, "max": 1.4244381189346313, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71160.4375, "min": 68437.390625, "max": 76463.3671875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.23355263157895, "min": 79.27331189710611, "max": 433.5431034482759, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49390.0, "min": 48828.0, "max": 50291.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999945.0, "min": 49910.0, "max": 1999945.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999945.0, "min": 49910.0, "max": 1999945.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4018666744232178, "min": 0.10458787530660629, "max": 2.5182361602783203, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1460.3349609375, "min": 12.027606010437012, "max": 1503.525634765625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.68131585419178, "min": 1.8628600672535274, "max": 4.0777835572633245, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2238.2400393486023, "min": 214.22890773415565, "max": 2414.639063179493, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.68131585419178, "min": 1.8628600672535274, "max": 4.0777835572633245, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2238.2400393486023, "min": 214.22890773415565, "max": 2414.639063179493, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015542928398483329, "min": 0.013308291626344726, "max": 0.019573095124602938, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04662878519544999, "min": 0.026616583252689452, "max": 0.05661474285249521, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06106625588403808, "min": 0.021062691261370975, "max": 0.06403052533666292, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18319876765211424, "min": 0.04212538252274195, "max": 0.18319876765211424, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.474798841766675e-06, "min": 3.474798841766675e-06, "max": 0.000295269076576975, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0424396525300026e-05, "min": 1.0424396525300026e-05, "max": 0.00084367966877345, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10115823333333335, "min": 0.10115823333333335, "max": 0.19842302499999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30347470000000004, "min": 0.20744794999999994, "max": 0.5812265499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.779584333333349e-05, "min": 6.779584333333349e-05, "max": 0.0049213089475, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020338753000000045, "min": 0.00020338753000000045, "max": 0.014063204845, "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": "1670592487", "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": "1670594656" }, "total": 2168.318355204, "count": 1, "self": 0.3955913789995975, "children": { "run_training.setup": { "total": 0.11257934599996133, "count": 1, "self": 0.11257934599996133 }, "TrainerController.start_learning": { "total": 2167.8101844790003, "count": 1, "self": 3.815561035997689, "children": { "TrainerController._reset_env": { "total": 10.72575757300001, "count": 1, "self": 10.72575757300001 }, "TrainerController.advance": { "total": 2153.154193368003, "count": 233034, "self": 4.137912956957734, "children": { "env_step": { "total": 1692.3106204768721, "count": 233034, "self": 1419.1898220758903, "children": { "SubprocessEnvManager._take_step": { "total": 270.6339584889241, "count": 233034, "self": 13.830718851837219, "children": { "TorchPolicy.evaluate": { "total": 256.8032396370869, "count": 222970, "self": 65.77078303400117, "children": { "TorchPolicy.sample_actions": { "total": 191.03245660308573, "count": 222970, "self": 191.03245660308573 } } } } }, "workers": { "total": 2.4868399120576896, "count": 233034, "self": 0.0, "children": { "worker_root": { "total": 2160.0498151618253, "count": 233034, "is_parallel": true, "self": 993.6034154038773, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017311960000370163, "count": 1, "is_parallel": true, "self": 0.00028852200011897366, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014426739999180427, "count": 2, "is_parallel": true, "self": 0.0014426739999180427 } } }, "UnityEnvironment.step": { "total": 0.02592183000001569, "count": 1, "is_parallel": true, "self": 0.00026360100002875697, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023233000001710025, "count": 1, "is_parallel": true, "self": 0.00023233000001710025 }, "communicator.exchange": { "total": 0.024741707999965, "count": 1, "is_parallel": true, "self": 0.024741707999965 }, "steps_from_proto": { "total": 0.0006841910000048301, "count": 1, "is_parallel": true, "self": 0.00022246399998948618, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046172700001534395, "count": 2, "is_parallel": true, "self": 0.00046172700001534395 } } } } } } }, "UnityEnvironment.step": { "total": 1166.446399757948, "count": 233033, "is_parallel": true, "self": 33.920391167962634, "children": { "UnityEnvironment._generate_step_input": { "total": 75.13313048097007, "count": 233033, "is_parallel": true, "self": 75.13313048097007 }, "communicator.exchange": { "total": 966.423311594013, "count": 233033, "is_parallel": true, "self": 966.423311594013 }, "steps_from_proto": { "total": 90.96956651500238, "count": 233033, "is_parallel": true, "self": 37.20224535683394, "children": { "_process_rank_one_or_two_observation": { "total": 53.76732115816844, "count": 466066, "is_parallel": true, "self": 53.76732115816844 } } } } } } } } } } }, "trainer_advance": { "total": 456.7056599341729, "count": 233034, "self": 5.753345475082938, "children": { "process_trajectory": { "total": 145.37463832409105, "count": 233034, "self": 144.89460178109073, "children": { "RLTrainer._checkpoint": { "total": 0.48003654300032395, "count": 4, "self": 0.48003654300032395 } } }, "_update_policy": { "total": 305.5776761349989, "count": 97, "self": 253.31823091199658, "children": { "TorchPPOOptimizer.update": { "total": 52.25944522300233, "count": 2910, "self": 52.25944522300233 } } } } } } }, "trainer_threads": { "total": 7.989997357071843e-07, "count": 1, "self": 7.989997357071843e-07 }, "TrainerController._save_models": { "total": 0.11467170300011276, "count": 1, "self": 0.0019472980002319673, "children": { "RLTrainer._checkpoint": { "total": 0.11272440499988079, "count": 1, "self": 0.11272440499988079 } } } } } } }