{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4094408750534058, "min": 1.4094408750534058, "max": 1.432161569595337, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71364.21875, "min": 68955.6953125, "max": 78113.109375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.69370860927152, "min": 79.3317230273752, "max": 402.288, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49343.0, "min": 49032.0, "max": 50286.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999958.0, "min": 49940.0, "max": 1999958.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999958.0, "min": 49940.0, "max": 1999958.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.412579298019409, "min": 0.10674311965703964, "max": 2.517995595932007, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1457.1978759765625, "min": 13.236146926879883, "max": 1503.243408203125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.771782163752625, "min": 1.900857756935781, "max": 3.985933227746383, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2278.1564269065857, "min": 235.70636186003685, "max": 2379.0277656316757, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.771782163752625, "min": 1.900857756935781, "max": 3.985933227746383, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2278.1564269065857, "min": 235.70636186003685, "max": 2379.0277656316757, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016965796646319278, "min": 0.012657294032396748, "max": 0.01985419694812865, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050897389938957836, "min": 0.025314588064793496, "max": 0.05956259084438595, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.056517725148134766, "min": 0.02243187455460429, "max": 0.06547185232241948, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1695531754444043, "min": 0.04486374910920858, "max": 0.19641555696725843, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.598548800516665e-06, "min": 3.598548800516665e-06, "max": 0.00029530537656487503, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0795646401549995e-05, "min": 1.0795646401549995e-05, "max": 0.00084406606864465, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10119948333333334, "min": 0.10119948333333334, "max": 0.198435125, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30359845, "min": 0.20752765, "max": 0.5813553499999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.985421833333329e-05, "min": 6.985421833333329e-05, "max": 0.004921912737500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020956265499999987, "min": 0.00020956265499999987, "max": 0.014069631965000001, "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": "1709977484", "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": "1709979457" }, "total": 1972.86853526, "count": 1, "self": 0.3217673479998666, "children": { "run_training.setup": { "total": 0.05345218900004056, "count": 1, "self": 0.05345218900004056 }, "TrainerController.start_learning": { "total": 1972.4933157230003, "count": 1, "self": 4.033581854981776, "children": { "TrainerController._reset_env": { "total": 2.6245545169999787, "count": 1, "self": 2.6245545169999787 }, "TrainerController.advance": { "total": 1965.7257741310184, "count": 232561, "self": 4.042191399988496, "children": { "env_step": { "total": 1538.634329435068, "count": 232561, "self": 1240.291398496886, "children": { "SubprocessEnvManager._take_step": { "total": 295.766056796061, "count": 232561, "self": 14.965607079078723, "children": { "TorchPolicy.evaluate": { "total": 280.80044971698226, "count": 223001, "self": 280.80044971698226 } } }, "workers": { "total": 2.5768741421211416, "count": 232561, "self": 0.0, "children": { "worker_root": { "total": 1965.410706534979, "count": 232561, "is_parallel": true, "self": 975.7094582239677, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008779570000569947, "count": 1, "is_parallel": true, "self": 0.00023041600013584684, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006475409999211479, "count": 2, "is_parallel": true, "self": 0.0006475409999211479 } } }, "UnityEnvironment.step": { "total": 0.021855254000001878, "count": 1, "is_parallel": true, "self": 0.0002760989999615049, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00015993099998468097, "count": 1, "is_parallel": true, "self": 0.00015993099998468097 }, "communicator.exchange": { "total": 0.02091018700002678, "count": 1, "is_parallel": true, "self": 0.02091018700002678 }, "steps_from_proto": { "total": 0.0005090370000289113, "count": 1, "is_parallel": true, "self": 0.00013965400000870432, "children": { "_process_rank_one_or_two_observation": { "total": 0.00036938300002020696, "count": 2, "is_parallel": true, "self": 0.00036938300002020696 } } } } } } }, "UnityEnvironment.step": { "total": 989.7012483110113, "count": 232560, "is_parallel": true, "self": 25.98237408310979, "children": { "UnityEnvironment._generate_step_input": { "total": 52.959007678946136, "count": 232560, "is_parallel": true, "self": 52.959007678946136 }, "communicator.exchange": { "total": 850.8441899820202, "count": 232560, "is_parallel": true, "self": 850.8441899820202 }, "steps_from_proto": { "total": 59.91567656693519, "count": 232560, "is_parallel": true, "self": 23.222207306163114, "children": { "_process_rank_one_or_two_observation": { "total": 36.693469260772076, "count": 465120, "is_parallel": true, "self": 36.693469260772076 } } } } } } } } } } }, "trainer_advance": { "total": 423.049253295962, "count": 232561, "self": 6.070492020911047, "children": { "process_trajectory": { "total": 138.6901150230492, "count": 232561, "self": 137.55448844504986, "children": { "RLTrainer._checkpoint": { "total": 1.1356265779993464, "count": 10, "self": 1.1356265779993464 } } }, "_update_policy": { "total": 278.28864625200174, "count": 97, "self": 231.21629439400567, "children": { "TorchPPOOptimizer.update": { "total": 47.07235185799607, "count": 2910, "self": 47.07235185799607 } } } } } } }, "trainer_threads": { "total": 9.99999883788405e-07, "count": 1, "self": 9.99999883788405e-07 }, "TrainerController._save_models": { "total": 0.10940422000021499, "count": 1, "self": 0.0019924670004911604, "children": { "RLTrainer._checkpoint": { "total": 0.10741175299972383, "count": 1, "self": 0.10741175299972383 } } } } } } }