{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3986119031906128, "min": 1.3986119031906128, "max": 1.4272193908691406, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69909.6171875, "min": 68980.515625, "max": 76948.8203125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 74.85887708649469, "min": 71.59071117561683, "max": 407.0731707317073, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49332.0, "min": 48797.0, "max": 50070.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999930.0, "min": 49782.0, "max": 1999930.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999930.0, "min": 49782.0, "max": 1999930.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4748716354370117, "min": -0.009717012755572796, "max": 2.5046610832214355, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1630.9404296875, "min": -1.1854755878448486, "max": 1703.673828125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.863484154883574, "min": 1.8489029527199072, "max": 4.017217723283911, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2546.0360580682755, "min": 225.5661602318287, "max": 2615.5263051986694, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.863484154883574, "min": 1.8489029527199072, "max": 4.017217723283911, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2546.0360580682755, "min": 225.5661602318287, "max": 2615.5263051986694, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015541410738822177, "min": 0.012846298208589561, "max": 0.020392909957445228, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.046624232216466534, "min": 0.02715820744560915, "max": 0.057562461139961364, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05791126021908389, "min": 0.024869270933171116, "max": 0.06369256221999725, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17373378065725167, "min": 0.04973854186634223, "max": 0.18548102130492528, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.926398691233338e-06, "min": 3.926398691233338e-06, "max": 0.000295387726537425, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1779196073700013e-05, "min": 1.1779196073700013e-05, "max": 0.00084447466850845, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10130876666666665, "min": 0.10130876666666665, "max": 0.19846257499999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3039262999999999, "min": 0.20775120000000002, "max": 0.5814915500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.530745666666678e-05, "min": 7.530745666666678e-05, "max": 0.0049232824925, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022592237000000032, "min": 0.00022592237000000032, "max": 0.014076428344999996, "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": "1724096947", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724099356" }, "total": 2408.986247542, "count": 1, "self": 0.4427949030000491, "children": { "run_training.setup": { "total": 0.058424556999966626, "count": 1, "self": 0.058424556999966626 }, "TrainerController.start_learning": { "total": 2408.485028082, "count": 1, "self": 4.405687960121213, "children": { "TrainerController._reset_env": { "total": 2.704635742999926, "count": 1, "self": 2.704635742999926 }, "TrainerController.advance": { "total": 2401.264632557879, "count": 232843, "self": 5.003428151972912, "children": { "env_step": { "total": 1898.0806372418672, "count": 232843, "self": 1563.6740324176942, "children": { "SubprocessEnvManager._take_step": { "total": 331.52968991307523, "count": 232843, "self": 17.26057462911956, "children": { "TorchPolicy.evaluate": { "total": 314.26911528395567, "count": 222868, "self": 314.26911528395567 } } }, "workers": { "total": 2.8769149110977423, "count": 232843, "self": 0.0, "children": { "worker_root": { "total": 2401.222506307028, "count": 232843, "is_parallel": true, "self": 1140.0579356769776, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008576300000413539, "count": 1, "is_parallel": true, "self": 0.00023306299999603652, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006245670000453174, "count": 2, "is_parallel": true, "self": 0.0006245670000453174 } } }, "UnityEnvironment.step": { "total": 0.028529405999961455, "count": 1, "is_parallel": true, "self": 0.000368550999951367, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023145199997998134, "count": 1, "is_parallel": true, "self": 0.00023145199997998134 }, "communicator.exchange": { "total": 0.027188260999992053, "count": 1, "is_parallel": true, "self": 0.027188260999992053 }, "steps_from_proto": { "total": 0.0007411420000380531, "count": 1, "is_parallel": true, "self": 0.00020010400010050944, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005410379999375436, "count": 2, "is_parallel": true, "self": 0.0005410379999375436 } } } } } } }, "UnityEnvironment.step": { "total": 1261.1645706300505, "count": 232842, "is_parallel": true, "self": 38.45945179221826, "children": { "UnityEnvironment._generate_step_input": { "total": 79.20543157889131, "count": 232842, "is_parallel": true, "self": 79.20543157889131 }, "communicator.exchange": { "total": 1054.0489979159247, "count": 232842, "is_parallel": true, "self": 1054.0489979159247 }, "steps_from_proto": { "total": 89.45068934301605, "count": 232842, "is_parallel": true, "self": 31.83942659090951, "children": { "_process_rank_one_or_two_observation": { "total": 57.61126275210654, "count": 465684, "is_parallel": true, "self": 57.61126275210654 } } } } } } } } } } }, "trainer_advance": { "total": 498.18056716403885, "count": 232843, "self": 6.787140146057482, "children": { "process_trajectory": { "total": 158.68227981397922, "count": 232843, "self": 157.42939257697913, "children": { "RLTrainer._checkpoint": { "total": 1.2528872370000954, "count": 10, "self": 1.2528872370000954 } } }, "_update_policy": { "total": 332.71114720400215, "count": 97, "self": 268.575997863001, "children": { "TorchPPOOptimizer.update": { "total": 64.13514934100112, "count": 2910, "self": 64.13514934100112 } } } } } } }, "trainer_threads": { "total": 8.810002327663824e-07, "count": 1, "self": 8.810002327663824e-07 }, "TrainerController._save_models": { "total": 0.11007093999978679, "count": 1, "self": 0.002672168999652058, "children": { "RLTrainer._checkpoint": { "total": 0.10739877100013473, "count": 1, "self": 0.10739877100013473 } } } } } } }