{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.406558632850647, "min": 1.406558632850647, "max": 1.4299204349517822, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69962.2265625, "min": 68913.0234375, "max": 75855.8515625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 69.70579915134371, "min": 69.08415147265077, "max": 393.66141732283467, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49282.0, "min": 49255.0, "max": 49995.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999897.0, "min": 49964.0, "max": 1999897.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999897.0, "min": 49964.0, "max": 1999897.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4701650142669678, "min": 0.09568103402853012, "max": 2.565108299255371, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1746.40673828125, "min": 12.05580997467041, "max": 1768.527099609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7902789861174586, "min": 1.8893226318889194, "max": 4.084103101839399, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2679.7272431850433, "min": 238.05465161800385, "max": 2734.252792239189, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7902789861174586, "min": 1.8893226318889194, "max": 4.084103101839399, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2679.7272431850433, "min": 238.05465161800385, "max": 2734.252792239189, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017649862397269723, "min": 0.014843134188009166, "max": 0.01936295936078144, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.052949587191809165, "min": 0.03031601365679914, "max": 0.05709063568065176, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06110878495706452, "min": 0.023112626622120536, "max": 0.0642408747639921, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18332635487119356, "min": 0.0462853771323959, "max": 0.19272262429197629, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6323487892499927e-06, "min": 3.6323487892499927e-06, "max": 0.0002953256265581249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0897046367749978e-05, "min": 1.0897046367749978e-05, "max": 0.0008438532187156001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10121074999999997, "min": 0.10121074999999997, "max": 0.198441875, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30363224999999994, "min": 0.20754530000000004, "max": 0.5812844000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.041642499999987e-05, "min": 7.041642499999987e-05, "max": 0.0049222495625000015, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002112492749999996, "min": 0.0002112492749999996, "max": 0.014066091559999997, "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": "1678102378", "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": "1678104794" }, "total": 2415.773162674, "count": 1, "self": 0.44620619799979977, "children": { "run_training.setup": { "total": 0.11224531700008811, "count": 1, "self": 0.11224531700008811 }, "TrainerController.start_learning": { "total": 2415.214711159, "count": 1, "self": 4.366681863903068, "children": { "TrainerController._reset_env": { "total": 10.323190581999938, "count": 1, "self": 10.323190581999938 }, "TrainerController.advance": { "total": 2400.4159282990972, "count": 233731, "self": 4.364049907118442, "children": { "env_step": { "total": 1860.4097491809248, "count": 233731, "self": 1554.2352118249137, "children": { "SubprocessEnvManager._take_step": { "total": 303.3977579560035, "count": 233731, "self": 15.92441250702052, "children": { "TorchPolicy.evaluate": { "total": 287.47334544898297, "count": 222922, "self": 71.96291804296288, "children": { "TorchPolicy.sample_actions": { "total": 215.51042740602009, "count": 222922, "self": 215.51042740602009 } } } } }, "workers": { "total": 2.7767794000076265, "count": 233731, "self": 0.0, "children": { "worker_root": { "total": 2406.7687045709754, "count": 233731, "is_parallel": true, "self": 1140.8486294079858, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009040830000230926, "count": 1, "is_parallel": true, "self": 0.00033920200007742096, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005648809999456716, "count": 2, "is_parallel": true, "self": 0.0005648809999456716 } } }, "UnityEnvironment.step": { "total": 0.028625689000023158, "count": 1, "is_parallel": true, "self": 0.00029196000014053425, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022296499992080498, "count": 1, "is_parallel": true, "self": 0.00022296499992080498 }, "communicator.exchange": { "total": 0.027404898999975558, "count": 1, "is_parallel": true, "self": 0.027404898999975558 }, "steps_from_proto": { "total": 0.000705864999986261, "count": 1, "is_parallel": true, "self": 0.00022936399989248457, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004765010000937764, "count": 2, "is_parallel": true, "self": 0.0004765010000937764 } } } } } } }, "UnityEnvironment.step": { "total": 1265.9200751629896, "count": 233730, "is_parallel": true, "self": 39.60750494503509, "children": { "UnityEnvironment._generate_step_input": { "total": 79.9476369491224, "count": 233730, "is_parallel": true, "self": 79.9476369491224 }, "communicator.exchange": { "total": 1054.6497833108579, "count": 233730, "is_parallel": true, "self": 1054.6497833108579 }, "steps_from_proto": { "total": 91.71514995797429, "count": 233730, "is_parallel": true, "self": 36.98849768796333, "children": { "_process_rank_one_or_two_observation": { "total": 54.72665227001096, "count": 467460, "is_parallel": true, "self": 54.72665227001096 } } } } } } } } } } }, "trainer_advance": { "total": 535.642129211054, "count": 233731, "self": 6.320856537010513, "children": { "process_trajectory": { "total": 169.69516209604524, "count": 233731, "self": 168.49615002904466, "children": { "RLTrainer._checkpoint": { "total": 1.1990120670005808, "count": 10, "self": 1.1990120670005808 } } }, "_update_policy": { "total": 359.62611057799825, "count": 97, "self": 301.90562156799433, "children": { "TorchPPOOptimizer.update": { "total": 57.72048901000392, "count": 2910, "self": 57.72048901000392 } } } } } } }, "trainer_threads": { "total": 9.37000095291296e-07, "count": 1, "self": 9.37000095291296e-07 }, "TrainerController._save_models": { "total": 0.10890947699999742, "count": 1, "self": 0.002599862999886682, "children": { "RLTrainer._checkpoint": { "total": 0.10630961400011074, "count": 1, "self": 0.10630961400011074 } } } } } } }