{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5365502238273621, "min": 0.5365502238273621, "max": 1.4933209419250488, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16130.845703125, "min": 16130.845703125, "max": 45301.3828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989962.0, "min": 29952.0, "max": 989962.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989962.0, "min": 29952.0, "max": 989962.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.06402862071990967, "min": -0.10768884420394897, "max": 0.09902215749025345, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 15.815069198608398, "min": -25.95301055908203, "max": 24.656517028808594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.048150576651096344, "min": -0.048150576651096344, "max": 0.1367024928331375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -11.893192291259766, "min": -11.893192291259766, "max": 32.9453010559082, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06799920988924599, "min": 0.06453638719316358, "max": 0.07324390831351811, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9519889384494438, "min": 0.4939414654238198, "max": 1.0181615443103582, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008312903345578904, "min": 0.0005193653563030646, "max": 0.008312903345578904, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11638064683810465, "min": 0.007271114988242905, "max": 0.11638064683810465, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.694840292228573e-06, "min": 7.694840292228573e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010772776409120003, "min": 0.00010772776409120003, "max": 0.0033718342760553, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10256491428571425, "min": 0.10256491428571425, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4359087999999995, "min": 1.3886848, "max": 2.4431751000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026623493714285725, "min": 0.00026623493714285725, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037272891200000016, "min": 0.0037272891200000016, "max": 0.11241207552999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011129645630717278, "min": 0.010585368610918522, "max": 0.3125114142894745, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1558150351047516, "min": 0.14819516241550446, "max": 2.187579870223999, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 835.6486486486486, "min": 760.2702702702703, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30919.0, "min": 15984.0, "max": 33099.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.07927570814216459, "min": -1.0000000521540642, "max": 0.39108417849791677, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -2.93320120126009, "min": -31.998401671648026, "max": 14.861198782920837, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.07927570814216459, "min": -1.0000000521540642, "max": 0.39108417849791677, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -2.93320120126009, "min": -31.998401671648026, "max": 14.861198782920837, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.09616883003075821, "min": 0.08563765169133265, "max": 6.396927391178906, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.558246711138054, "min": 3.1652114451280795, "max": 102.3508382588625, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1681761766", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1681763706" }, "total": 1940.016888574, "count": 1, "self": 0.4241349049998462, "children": { "run_training.setup": { "total": 0.11491569800000434, "count": 1, "self": 0.11491569800000434 }, "TrainerController.start_learning": { "total": 1939.477837971, "count": 1, "self": 1.2435745010684514, "children": { "TrainerController._reset_env": { "total": 3.767283196000335, "count": 1, "self": 3.767283196000335 }, "TrainerController.advance": { "total": 1934.3728557009322, "count": 63218, "self": 1.3089414289538581, "children": { "env_step": { "total": 1332.5932610970049, "count": 63218, "self": 1233.1490597651982, "children": { "SubprocessEnvManager._take_step": { "total": 98.69078752993164, "count": 63218, "self": 4.536203546865636, "children": { "TorchPolicy.evaluate": { "total": 94.154583983066, "count": 62566, "self": 94.154583983066 } } }, "workers": { "total": 0.7534138018750127, "count": 63218, "self": 0.0, "children": { "worker_root": { "total": 1935.13881596694, "count": 63218, "is_parallel": true, "self": 804.8891726078964, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017417100002603547, "count": 1, "is_parallel": true, "self": 0.0005532680002033885, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011884420000569662, "count": 8, "is_parallel": true, "self": 0.0011884420000569662 } } }, "UnityEnvironment.step": { "total": 0.04603518400017492, "count": 1, "is_parallel": true, "self": 0.0005344760002117255, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047093600005609915, "count": 1, "is_parallel": true, "self": 0.00047093600005609915 }, "communicator.exchange": { "total": 0.043420332000096096, "count": 1, "is_parallel": true, "self": 0.043420332000096096 }, "steps_from_proto": { "total": 0.001609439999811002, "count": 1, "is_parallel": true, "self": 0.0003687599996737845, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012406800001372176, "count": 8, "is_parallel": true, "self": 0.0012406800001372176 } } } } } } }, "UnityEnvironment.step": { "total": 1130.2496433590436, "count": 63217, "is_parallel": true, "self": 31.19939596012682, "children": { "UnityEnvironment._generate_step_input": { "total": 22.1983211360689, "count": 63217, "is_parallel": true, "self": 22.1983211360689 }, "communicator.exchange": { "total": 987.4359414758919, "count": 63217, "is_parallel": true, "self": 987.4359414758919 }, "steps_from_proto": { "total": 89.41598478695596, "count": 63217, "is_parallel": true, "self": 18.555440602806357, "children": { "_process_rank_one_or_two_observation": { "total": 70.8605441841496, "count": 505736, "is_parallel": true, "self": 70.8605441841496 } } } } } } } } } } }, "trainer_advance": { "total": 600.4706531749734, "count": 63218, "self": 2.2944297449262194, "children": { "process_trajectory": { "total": 99.7101897470443, "count": 63218, "self": 99.50453740804369, "children": { "RLTrainer._checkpoint": { "total": 0.20565233900060775, "count": 2, "self": 0.20565233900060775 } } }, "_update_policy": { "total": 498.46603368300293, "count": 444, "self": 321.74128852101694, "children": { "TorchPPOOptimizer.update": { "total": 176.724745161986, "count": 22806, "self": 176.724745161986 } } } } } } }, "trainer_threads": { "total": 9.959994713426568e-07, "count": 1, "self": 9.959994713426568e-07 }, "TrainerController._save_models": { "total": 0.09412357699966378, "count": 1, "self": 0.0016023460002543288, "children": { "RLTrainer._checkpoint": { "total": 0.09252123099940945, "count": 1, "self": 0.09252123099940945 } } } } } } }