{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4408644437789917, "min": 0.42947229743003845, "max": 1.4141699075698853, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13317.6328125, "min": 12904.783203125, "max": 42900.2578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989902.0, "min": 29978.0, "max": 989902.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989902.0, "min": 29978.0, "max": 989902.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.541954755783081, "min": -0.10700222104787827, "max": 0.6013885140419006, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 150.12147521972656, "min": -25.680532455444336, "max": 172.59849548339844, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.22872881591320038, "min": -0.050158582627773285, "max": 0.339653342962265, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 63.35788345336914, "min": -14.094561576843262, "max": 80.83749389648438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.066191993118329, "min": 0.06492571445618606, "max": 0.07484623532426278, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.926687903656606, "min": 0.655691298063867, "max": 1.0573457980137, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.019346639635133476, "min": 0.0009086861322041705, "max": 0.019346639635133476, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.27085295489186867, "min": 0.011812919718654216, "max": 0.27085295489186867, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.585918899964288e-06, "min": 7.585918899964288e-06, "max": 0.0002947946684017778, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010620286459950004, "min": 0.00010620286459950004, "max": 0.0033702337765887996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252860714285716, "min": 0.10252860714285716, "max": 0.19826488888888888, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354005000000003, "min": 1.4354005000000003, "max": 2.4851026, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002626078535714287, "min": 0.0002626078535714287, "max": 0.0098266624, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003676509950000002, "min": 0.003676509950000002, "max": 0.11235877888000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014929051510989666, "min": 0.014929051510989666, "max": 0.4865407943725586, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20900672674179077, "min": 0.20900672674179077, "max": 4.378867149353027, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 343.0348837209302, "min": 323.37894736842105, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29501.0, "min": 16649.0, "max": 34624.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5639139359253784, "min": -0.9999267183244228, "max": 1.6495180508817535, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 134.49659848958254, "min": -29.997801549732685, "max": 151.27739813923836, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5639139359253784, "min": -0.9999267183244228, "max": 1.6495180508817535, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 134.49659848958254, "min": -29.997801549732685, "max": 151.27739813923836, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05301745968811934, "min": 0.05301745968811934, "max": 9.523742860292687, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.559501533178263, "min": 4.559501533178263, "max": 161.90362862497568, "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": "1713568326", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1713570567" }, "total": 2241.220452488, "count": 1, "self": 0.5496301579996725, "children": { "run_training.setup": { "total": 0.06566828600000463, "count": 1, "self": 0.06566828600000463 }, "TrainerController.start_learning": { "total": 2240.6051540440003, "count": 1, "self": 1.496384301000944, "children": { "TrainerController._reset_env": { "total": 2.7525472119999677, "count": 1, "self": 2.7525472119999677 }, "TrainerController.advance": { "total": 2236.270054102999, "count": 63752, "self": 1.5458806870833541, "children": { "env_step": { "total": 1605.4348163589414, "count": 63752, "self": 1465.0216238409268, "children": { "SubprocessEnvManager._take_step": { "total": 139.4972773590083, "count": 63752, "self": 4.933222619997764, "children": { "TorchPolicy.evaluate": { "total": 134.56405473901054, "count": 62561, "self": 134.56405473901054 } } }, "workers": { "total": 0.9159151590062606, "count": 63752, "self": 0.0, "children": { "worker_root": { "total": 2235.059940187025, "count": 63752, "is_parallel": true, "self": 897.8295772210327, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007370608000030643, "count": 1, "is_parallel": true, "self": 0.0059211530000879975, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014494549999426454, "count": 8, "is_parallel": true, "self": 0.0014494549999426454 } } }, "UnityEnvironment.step": { "total": 0.048838774999978796, "count": 1, "is_parallel": true, "self": 0.0006762770000818819, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047091499999396547, "count": 1, "is_parallel": true, "self": 0.00047091499999396547 }, "communicator.exchange": { "total": 0.04592802099995197, "count": 1, "is_parallel": true, "self": 0.04592802099995197 }, "steps_from_proto": { "total": 0.00176356199995098, "count": 1, "is_parallel": true, "self": 0.0003811219999079185, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013824400000430614, "count": 8, "is_parallel": true, "self": 0.0013824400000430614 } } } } } } }, "UnityEnvironment.step": { "total": 1337.2303629659923, "count": 63751, "is_parallel": true, "self": 35.35223576702083, "children": { "UnityEnvironment._generate_step_input": { "total": 25.14631549196571, "count": 63751, "is_parallel": true, "self": 25.14631549196571 }, "communicator.exchange": { "total": 1170.6621731899909, "count": 63751, "is_parallel": true, "self": 1170.6621731899909 }, "steps_from_proto": { "total": 106.069638517015, "count": 63751, "is_parallel": true, "self": 21.924431654041996, "children": { "_process_rank_one_or_two_observation": { "total": 84.145206862973, "count": 510008, "is_parallel": true, "self": 84.145206862973 } } } } } } } } } } }, "trainer_advance": { "total": 629.2893570569743, "count": 63752, "self": 2.771614952942514, "children": { "process_trajectory": { "total": 131.4094964030341, "count": 63752, "self": 131.15070915603445, "children": { "RLTrainer._checkpoint": { "total": 0.2587872469996455, "count": 2, "self": 0.2587872469996455 } } }, "_update_policy": { "total": 495.10824570099766, "count": 455, "self": 289.13858853999295, "children": { "TorchPPOOptimizer.update": { "total": 205.9696571610047, "count": 22809, "self": 205.9696571610047 } } } } } } }, "trainer_threads": { "total": 1.0480002856638748e-06, "count": 1, "self": 1.0480002856638748e-06 }, "TrainerController._save_models": { "total": 0.08616738000000623, "count": 1, "self": 0.0014528599999721337, "children": { "RLTrainer._checkpoint": { "total": 0.0847145200000341, "count": 1, "self": 0.0847145200000341 } } } } } } }