{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4126352071762085, "min": 1.4126352071762085, "max": 1.4284579753875732, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71126.1796875, "min": 69082.9375, "max": 75942.890625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.87410071942446, "min": 76.88473520249221, "max": 402.9032258064516, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49414.0, "min": 48748.0, "max": 50004.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999913.0, "min": 49532.0, "max": 1999913.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999913.0, "min": 49532.0, "max": 1999913.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.474724769592285, "min": 0.14034946262836456, "max": 2.5029752254486084, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1375.947021484375, "min": 17.262983322143555, "max": 1563.0723876953125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.786517693306045, "min": 1.920349041378595, "max": 4.049099780849574, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2105.303837478161, "min": 236.20293208956718, "max": 2462.122134447098, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.786517693306045, "min": 1.920349041378595, "max": 4.049099780849574, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2105.303837478161, "min": 236.20293208956718, "max": 2462.122134447098, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.013147122854570625, "min": 0.013147122854570625, "max": 0.02059622086558698, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03944136856371187, "min": 0.029509618743516815, "max": 0.06178866259676094, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.052039391878578395, "min": 0.02255838718265295, "max": 0.05963707769082652, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15611817563573518, "min": 0.04550156282881895, "max": 0.17891123307247955, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6808987730666732e-06, "min": 3.6808987730666732e-06, "max": 0.000295370176543275, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.104269631920002e-05, "min": 1.104269631920002e-05, "max": 0.00084428776857075, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10122693333333337, "min": 0.10122693333333337, "max": 0.19845672499999994, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036808000000001, "min": 0.20758945, "max": 0.58142925, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.122397333333347e-05, "min": 7.122397333333347e-05, "max": 0.0049229905775, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021367192000000038, "min": 0.00021367192000000038, "max": 0.014073319575, "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": "1672489039", "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": "1672491280" }, "total": 2240.088361479, "count": 1, "self": 0.38960239500011085, "children": { "run_training.setup": { "total": 0.12552863099995193, "count": 1, "self": 0.12552863099995193 }, "TrainerController.start_learning": { "total": 2239.573230453, "count": 1, "self": 3.8378986560296653, "children": { "TrainerController._reset_env": { "total": 7.845828632000121, "count": 1, "self": 7.845828632000121 }, "TrainerController.advance": { "total": 2227.7788428549707, "count": 232946, "self": 4.035639523075588, "children": { "env_step": { "total": 1746.0946739688904, "count": 232946, "self": 1469.1751673137167, "children": { "SubprocessEnvManager._take_step": { "total": 274.3907516200479, "count": 232946, "self": 14.18756733716691, "children": { "TorchPolicy.evaluate": { "total": 260.203184282881, "count": 222974, "self": 65.54345947086404, "children": { "TorchPolicy.sample_actions": { "total": 194.65972481201698, "count": 222974, "self": 194.65972481201698 } } } } }, "workers": { "total": 2.5287550351258687, "count": 232946, "self": 0.0, "children": { "worker_root": { "total": 2231.793423109049, "count": 232946, "is_parallel": true, "self": 1019.3447609500031, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020985080000173184, "count": 1, "is_parallel": true, "self": 0.0003297989999282436, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017687090000890748, "count": 2, "is_parallel": true, "self": 0.0017687090000890748 } } }, "UnityEnvironment.step": { "total": 0.027522260000068854, "count": 1, "is_parallel": true, "self": 0.00028393200022946985, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003022319999672618, "count": 1, "is_parallel": true, "self": 0.0003022319999672618 }, "communicator.exchange": { "total": 0.02630284099996061, "count": 1, "is_parallel": true, "self": 0.02630284099996061 }, "steps_from_proto": { "total": 0.0006332549999115145, "count": 1, "is_parallel": true, "self": 0.00021419099994091084, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004190639999706036, "count": 2, "is_parallel": true, "self": 0.0004190639999706036 } } } } } } }, "UnityEnvironment.step": { "total": 1212.4486621590459, "count": 232945, "is_parallel": true, "self": 34.98509905202786, "children": { "UnityEnvironment._generate_step_input": { "total": 77.19828897603838, "count": 232945, "is_parallel": true, "self": 77.19828897603838 }, "communicator.exchange": { "total": 1006.2260167620132, "count": 232945, "is_parallel": true, "self": 1006.2260167620132 }, "steps_from_proto": { "total": 94.03925736896645, "count": 232945, "is_parallel": true, "self": 38.52699352083141, "children": { "_process_rank_one_or_two_observation": { "total": 55.512263848135035, "count": 465890, "is_parallel": true, "self": 55.512263848135035 } } } } } } } } } } }, "trainer_advance": { "total": 477.6485293630046, "count": 232946, "self": 5.94482128600248, "children": { "process_trajectory": { "total": 150.01994398600004, "count": 232946, "self": 148.83959181500063, "children": { "RLTrainer._checkpoint": { "total": 1.180352170999413, "count": 10, "self": 1.180352170999413 } } }, "_update_policy": { "total": 321.6837640910021, "count": 97, "self": 268.66725860100723, "children": { "TorchPPOOptimizer.update": { "total": 53.01650548999487, "count": 2910, "self": 53.01650548999487 } } } } } } }, "trainer_threads": { "total": 9.979999049392063e-07, "count": 1, "self": 9.979999049392063e-07 }, "TrainerController._save_models": { "total": 0.11065931199982515, "count": 1, "self": 0.0022738519996892137, "children": { "RLTrainer._checkpoint": { "total": 0.10838546000013594, "count": 1, "self": 0.10838546000013594 } } } } } } }