{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4054514169692993, "min": 1.4054514169692993, "max": 1.4250333309173584, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69211.453125, "min": 68754.53125, "max": 75816.296875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 82.13976705490849, "min": 81.39538714991762, "max": 389.765625, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49366.0, "min": 48920.0, "max": 50289.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999974.0, "min": 49269.0, "max": 1999974.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999974.0, "min": 49269.0, "max": 1999974.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4268722534179688, "min": 0.13791745901107788, "max": 2.4703516960144043, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1458.55029296875, "min": 17.515518188476562, "max": 1467.388916015625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7101191106731206, "min": 1.8905257500532104, "max": 3.908929330440378, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2229.7815855145454, "min": 240.09677025675774, "max": 2296.3824159502983, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7101191106731206, "min": 1.8905257500532104, "max": 3.908929330440378, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2229.7815855145454, "min": 240.09677025675774, "max": 2296.3824159502983, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016643344914943254, "min": 0.013405064193890816, "max": 0.01860785258920967, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04993003474482976, "min": 0.02743581121030729, "max": 0.055823557767629005, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05994820238815413, "min": 0.021221786240736645, "max": 0.06010984797030687, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1798446071644624, "min": 0.04244357248147329, "max": 0.1798446071644624, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.540348819916667e-06, "min": 3.540348819916667e-06, "max": 0.00029527545157484995, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0621046459750002e-05, "min": 1.0621046459750002e-05, "max": 0.00084409846863385, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10118008333333335, "min": 0.10118008333333335, "max": 0.19842515, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30354025000000007, "min": 0.20750840000000004, "max": 0.58136615, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.888615833333335e-05, "min": 6.888615833333335e-05, "max": 0.004921414985, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020665847500000003, "min": 0.00020665847500000003, "max": 0.014070170885000004, "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": "1712819505", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712821942" }, "total": 2436.4001182829998, "count": 1, "self": 0.5817139229998247, "children": { "run_training.setup": { "total": 0.06291662799992537, "count": 1, "self": 0.06291662799992537 }, "TrainerController.start_learning": { "total": 2435.755487732, "count": 1, "self": 4.365476774922172, "children": { "TrainerController._reset_env": { "total": 2.7943308650000063, "count": 1, "self": 2.7943308650000063 }, "TrainerController.advance": { "total": 2428.4333590200777, "count": 232374, "self": 4.648270366101315, "children": { "env_step": { "total": 1951.6893387910293, "count": 232374, "self": 1620.4436424578355, "children": { "SubprocessEnvManager._take_step": { "total": 328.3635702040856, "count": 232374, "self": 16.795466148037804, "children": { "TorchPolicy.evaluate": { "total": 311.5681040560478, "count": 222866, "self": 311.5681040560478 } } }, "workers": { "total": 2.882126129108201, "count": 232374, "self": 0.0, "children": { "worker_root": { "total": 2428.3099174458325, "count": 232374, "is_parallel": true, "self": 1120.2759230338627, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009186199999930977, "count": 1, "is_parallel": true, "self": 0.00024188700001559482, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006767329999775029, "count": 2, "is_parallel": true, "self": 0.0006767329999775029 } } }, "UnityEnvironment.step": { "total": 0.0350721039999371, "count": 1, "is_parallel": true, "self": 0.0003971040000578796, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019506899991483806, "count": 1, "is_parallel": true, "self": 0.00019506899991483806 }, "communicator.exchange": { "total": 0.03367128699994737, "count": 1, "is_parallel": true, "self": 0.03367128699994737 }, "steps_from_proto": { "total": 0.0008086440000170114, "count": 1, "is_parallel": true, "self": 0.00020035300008203194, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006082909999349795, "count": 2, "is_parallel": true, "self": 0.0006082909999349795 } } } } } } }, "UnityEnvironment.step": { "total": 1308.0339944119698, "count": 232373, "is_parallel": true, "self": 39.99827476079531, "children": { "UnityEnvironment._generate_step_input": { "total": 86.93585819104987, "count": 232373, "is_parallel": true, "self": 86.93585819104987 }, "communicator.exchange": { "total": 1087.3718920771212, "count": 232373, "is_parallel": true, "self": 1087.3718920771212 }, "steps_from_proto": { "total": 93.7279693830036, "count": 232373, "is_parallel": true, "self": 35.23316674091609, "children": { "_process_rank_one_or_two_observation": { "total": 58.49480264208751, "count": 464746, "is_parallel": true, "self": 58.49480264208751 } } } } } } } } } } }, "trainer_advance": { "total": 472.09574986294683, "count": 232374, "self": 6.5428267768376145, "children": { "process_trajectory": { "total": 160.9734644571099, "count": 232374, "self": 159.6147574841102, "children": { "RLTrainer._checkpoint": { "total": 1.3587069729996983, "count": 10, "self": 1.3587069729996983 } } }, "_update_policy": { "total": 304.5794586289993, "count": 97, "self": 243.54396321301044, "children": { "TorchPPOOptimizer.update": { "total": 61.03549541598886, "count": 2910, "self": 61.03549541598886 } } } } } } }, "trainer_threads": { "total": 1.3660001059179194e-06, "count": 1, "self": 1.3660001059179194e-06 }, "TrainerController._save_models": { "total": 0.1623197059998347, "count": 1, "self": 0.0028008339995722054, "children": { "RLTrainer._checkpoint": { "total": 0.1595188720002625, "count": 1, "self": 0.1595188720002625 } } } } } } }