{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4000006318092346, "min": 0.39381349086761475, "max": 1.4236695766448975, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12006.4189453125, "min": 11803.9375, "max": 43188.44140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989987.0, "min": 29952.0, "max": 989987.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5424432754516602, "min": -0.12243293225765228, "max": 0.5774546265602112, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 146.45968627929688, "min": -29.38390350341797, "max": 161.6873016357422, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03748423606157303, "min": -0.012449697591364384, "max": 0.47741296887397766, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 10.120743751525879, "min": -3.4236669540405273, "max": 113.1468734741211, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06680681396909575, "min": 0.0654526676431, "max": 0.07283779605835056, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0021022095364363, "min": 0.49901582927298577, "max": 1.0925669408752583, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01468015397226231, "min": 0.0008968110473835752, "max": 0.016861734270129262, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22020230958393466, "min": 0.011658543615986477, "max": 0.2360642797818097, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.543497485533336e-06, "min": 7.543497485533336e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011315246228300004, "min": 0.00011315246228300004, "max": 0.0035081894306035998, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251446666666666, "min": 0.10251446666666666, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.537717, "min": 1.3886848, "max": 2.5693964000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026119522000000013, "min": 0.00026119522000000013, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003917928300000002, "min": 0.003917928300000002, "max": 0.11696270036, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010532126761972904, "min": 0.010532126761972904, "max": 0.5409807562828064, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15798190236091614, "min": 0.1476326286792755, "max": 3.786865234375, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 364.0843373493976, "min": 296.125, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30219.0, "min": 15984.0, "max": 32558.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4649975435217706, "min": -1.0000000521540642, "max": 1.665401907136234, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 120.12979856878519, "min": -29.966001711785793, "max": 173.20179834216833, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4649975435217706, "min": -1.0000000521540642, "max": 1.665401907136234, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 120.12979856878519, "min": -29.966001711785793, "max": 173.20179834216833, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.040216168908334175, "min": 0.03224950186211992, "max": 11.467996617779136, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2977258504834026, "min": 3.25139856262831, "max": 183.48794588446617, "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": "1710019337", "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/PyramidsRND.yaml --env=./ml-agents/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": "1710021003" }, "total": 1665.596765084, "count": 1, "self": 0.3225418819999959, "children": { "run_training.setup": { "total": 0.05535140999995747, "count": 1, "self": 0.05535140999995747 }, "TrainerController.start_learning": { "total": 1665.218871792, "count": 1, "self": 1.3927461119440068, "children": { "TrainerController._reset_env": { "total": 2.689754037999819, "count": 1, "self": 2.689754037999819 }, "TrainerController.advance": { "total": 1661.055175433056, "count": 63822, "self": 1.4203595619831049, "children": { "env_step": { "total": 1093.1389505460415, "count": 63822, "self": 970.130779234054, "children": { "SubprocessEnvManager._take_step": { "total": 122.15643736102925, "count": 63822, "self": 4.432992635017172, "children": { "TorchPolicy.evaluate": { "total": 117.72344472601208, "count": 62572, "self": 117.72344472601208 } } }, "workers": { "total": 0.8517339509583053, "count": 63822, "self": 0.0, "children": { "worker_root": { "total": 1663.0478068519815, "count": 63822, "is_parallel": true, "self": 793.6898622439733, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020838319999256782, "count": 1, "is_parallel": true, "self": 0.0006082719996811647, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014755600002445135, "count": 8, "is_parallel": true, "self": 0.0014755600002445135 } } }, "UnityEnvironment.step": { "total": 0.03724802099986846, "count": 1, "is_parallel": true, "self": 0.00046398099971156626, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002993470000092202, "count": 1, "is_parallel": true, "self": 0.0002993470000092202 }, "communicator.exchange": { "total": 0.03525309700012258, "count": 1, "is_parallel": true, "self": 0.03525309700012258 }, "steps_from_proto": { "total": 0.0012315960000250925, "count": 1, "is_parallel": true, "self": 0.0002958490001674363, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009357469998576562, "count": 8, "is_parallel": true, "self": 0.0009357469998576562 } } } } } } }, "UnityEnvironment.step": { "total": 869.3579446080082, "count": 63821, "is_parallel": true, "self": 23.083619499973338, "children": { "UnityEnvironment._generate_step_input": { "total": 14.510992326042924, "count": 63821, "is_parallel": true, "self": 14.510992326042924 }, "communicator.exchange": { "total": 768.3707896559838, "count": 63821, "is_parallel": true, "self": 768.3707896559838 }, "steps_from_proto": { "total": 63.39254312600815, "count": 63821, "is_parallel": true, "self": 13.68275536484066, "children": { "_process_rank_one_or_two_observation": { "total": 49.70978776116749, "count": 510568, "is_parallel": true, "self": 49.70978776116749 } } } } } } } } } } }, "trainer_advance": { "total": 566.4958653250314, "count": 63822, "self": 2.6890046460284793, "children": { "process_trajectory": { "total": 113.81007457900455, "count": 63822, "self": 113.62625598000454, "children": { "RLTrainer._checkpoint": { "total": 0.18381859900000563, "count": 2, "self": 0.18381859900000563 } } }, "_update_policy": { "total": 449.9967860999984, "count": 448, "self": 260.83208362497, "children": { "TorchPPOOptimizer.update": { "total": 189.16470247502843, "count": 22812, "self": 189.16470247502843 } } } } } } }, "trainer_threads": { "total": 9.79000105871819e-07, "count": 1, "self": 9.79000105871819e-07 }, "TrainerController._save_models": { "total": 0.08119523000004847, "count": 1, "self": 0.0014002650000293215, "children": { "RLTrainer._checkpoint": { "total": 0.07979496500001915, "count": 1, "self": 0.07979496500001915 } } } } } } }