{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4053518772125244, "min": 1.4053518772125244, "max": 1.4308953285217285, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69688.5859375, "min": 68662.4375, "max": 78169.890625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 97.01764705882353, "min": 83.17171717171718, "max": 424.109243697479, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49479.0, "min": 48813.0, "max": 50469.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999916.0, "min": 49838.0, "max": 1999916.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999916.0, "min": 49838.0, "max": 1999916.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.357332229614258, "min": 0.1940331757068634, "max": 2.422971725463867, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1202.2393798828125, "min": 22.89591407775879, "max": 1416.935302734375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.576519626379013, "min": 1.7813254074525025, "max": 3.9796080649370262, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1824.0250094532967, "min": 210.1963980793953, "max": 2261.0962039232254, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.576519626379013, "min": 1.7813254074525025, "max": 3.9796080649370262, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1824.0250094532967, "min": 210.1963980793953, "max": 2261.0962039232254, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.013667445819818465, "min": 0.013667445819818465, "max": 0.01914104676494996, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0410023374594554, "min": 0.02774603883014303, "max": 0.055547526988084434, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04620972830388281, "min": 0.020386556784311928, "max": 0.05857649426907301, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.13862918491164844, "min": 0.040773113568623856, "max": 0.1684747022887071, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1769489410500097e-06, "min": 3.1769489410500097e-06, "max": 0.00029534505155165, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.53084682315003e-06, "min": 9.53084682315003e-06, "max": 0.0008441232186256, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10105895000000002, "min": 0.10105895000000002, "max": 0.19844835000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30317685000000005, "min": 0.20727260000000003, "max": 0.5813744000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.284160500000017e-05, "min": 6.284160500000017e-05, "max": 0.004922572665, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001885248150000005, "min": 0.0001885248150000005, "max": 0.014070582559999998, "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": "1678248817", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1678251317" }, "total": 2500.550535748, "count": 1, "self": 0.5952362819998598, "children": { "run_training.setup": { "total": 0.10926673900002015, "count": 1, "self": 0.10926673900002015 }, "TrainerController.start_learning": { "total": 2499.8460327270004, "count": 1, "self": 4.456642354907217, "children": { "TrainerController._reset_env": { "total": 10.401419748000023, "count": 1, "self": 10.401419748000023 }, "TrainerController.advance": { "total": 2484.825428870093, "count": 231929, "self": 4.839710199160891, "children": { "env_step": { "total": 1925.0282561639926, "count": 231929, "self": 1609.991780906025, "children": { "SubprocessEnvManager._take_step": { "total": 312.03929799297543, "count": 231929, "self": 16.722015842025996, "children": { "TorchPolicy.evaluate": { "total": 295.31728215094944, "count": 222904, "self": 74.1212354180231, "children": { "TorchPolicy.sample_actions": { "total": 221.19604673292633, "count": 222904, "self": 221.19604673292633 } } } } }, "workers": { "total": 2.9971772649921604, "count": 231929, "self": 0.0, "children": { "worker_root": { "total": 2490.9631029910543, "count": 231929, "is_parallel": true, "self": 1184.8993555751065, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009789509999791335, "count": 1, "is_parallel": true, "self": 0.000367496000023948, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006114549999551855, "count": 2, "is_parallel": true, "self": 0.0006114549999551855 } } }, "UnityEnvironment.step": { "total": 0.06549742300001071, "count": 1, "is_parallel": true, "self": 0.00032503600004929467, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001967999999692438, "count": 1, "is_parallel": true, "self": 0.0001967999999692438 }, "communicator.exchange": { "total": 0.06426637300000948, "count": 1, "is_parallel": true, "self": 0.06426637300000948 }, "steps_from_proto": { "total": 0.0007092139999826941, "count": 1, "is_parallel": true, "self": 0.0002358270000399898, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004733869999427043, "count": 2, "is_parallel": true, "self": 0.0004733869999427043 } } } } } } }, "UnityEnvironment.step": { "total": 1306.0637474159478, "count": 231928, "is_parallel": true, "self": 39.31855395901471, "children": { "UnityEnvironment._generate_step_input": { "total": 81.3289726089564, "count": 231928, "is_parallel": true, "self": 81.3289726089564 }, "communicator.exchange": { "total": 1091.2170359720103, "count": 231928, "is_parallel": true, "self": 1091.2170359720103 }, "steps_from_proto": { "total": 94.19918487596635, "count": 231928, "is_parallel": true, "self": 37.91358288395088, "children": { "_process_rank_one_or_two_observation": { "total": 56.28560199201547, "count": 463856, "is_parallel": true, "self": 56.28560199201547 } } } } } } } } } } }, "trainer_advance": { "total": 554.9574625069399, "count": 231929, "self": 7.168276507968358, "children": { "process_trajectory": { "total": 168.50298382597356, "count": 231929, "self": 168.00265453597393, "children": { "RLTrainer._checkpoint": { "total": 0.5003292899996268, "count": 4, "self": 0.5003292899996268 } } }, "_update_policy": { "total": 379.28620217299806, "count": 97, "self": 320.2163859620051, "children": { "TorchPPOOptimizer.update": { "total": 59.06981621099294, "count": 2910, "self": 59.06981621099294 } } } } } } }, "trainer_threads": { "total": 1.490999693487538e-06, "count": 1, "self": 1.490999693487538e-06 }, "TrainerController._save_models": { "total": 0.16254026300020996, "count": 1, "self": 0.003051195999887568, "children": { "RLTrainer._checkpoint": { "total": 0.1594890670003224, "count": 1, "self": 0.1594890670003224 } } } } } } }