{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5396291613578796, "min": 0.5396291613578796, "max": 1.449646234512329, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16024.828125, "min": 16024.828125, "max": 43976.46875, "count": 33 }, "Pyramids.Step.mean": { "value": 989965.0, "min": 29952.0, "max": 989965.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989965.0, "min": 29952.0, "max": 989965.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3453983664512634, "min": -0.11043086647987366, "max": 0.3719022274017334, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 89.45817565917969, "min": -26.172115325927734, "max": 98.55409240722656, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 1.5317012071609497, "min": -0.030698606744408607, "max": 1.5317012071609497, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 396.7106018066406, "min": -8.135130882263184, "max": 396.7106018066406, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06773502037787735, "min": 0.06409167696015697, "max": 0.07292012126142564, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9482902852902829, "min": 0.5104408488299794, "max": 1.0701256441922549, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.22083097674423463, "min": 0.0004093818227983255, "max": 0.22083097674423463, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 3.0916336744192847, "min": 0.005321963696378232, "max": 3.0916336744192847, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.63758316845714e-06, "min": 7.63758316845714e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010692616435839995, "min": 0.00010692616435839995, "max": 0.0035075624308125997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254582857142858, "min": 0.10254582857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356416, "min": 1.3886848, "max": 2.5691874000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002643282742857142, "min": 0.0002643282742857142, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003700595839999999, "min": 0.003700595839999999, "max": 0.11694182126, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009579457342624664, "min": 0.009579457342624664, "max": 0.49516361951828003, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1341124027967453, "min": 0.1341124027967453, "max": 3.4661452770233154, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 509.9818181818182, "min": 461.3529411764706, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28049.0, "min": 15984.0, "max": 32676.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1262545203620737, "min": -1.0000000521540642, "max": 1.3032764412243576, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 61.943998619914055, "min": -28.050001703202724, "max": 88.62279800325632, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1262545203620737, "min": -1.0000000521540642, "max": 1.3032764412243576, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 61.943998619914055, "min": -28.050001703202724, "max": 88.62279800325632, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.050232053010073614, "min": 0.04731789393768208, "max": 10.204777055419981, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.762762915554049, "min": 2.762762915554049, "max": 163.2764328867197, "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": "1678490013", "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": "1678491991" }, "total": 1977.7811619940003, "count": 1, "self": 0.4309009349999542, "children": { "run_training.setup": { "total": 0.1051662770000803, "count": 1, "self": 0.1051662770000803 }, "TrainerController.start_learning": { "total": 1977.2450947820003, "count": 1, "self": 1.2969493809737287, "children": { "TrainerController._reset_env": { "total": 6.036467545999585, "count": 1, "self": 6.036467545999585 }, "TrainerController.advance": { "total": 1969.820643755027, "count": 63411, "self": 1.4133736250851143, "children": { "env_step": { "total": 1355.7575151389624, "count": 63411, "self": 1251.348787010871, "children": { "SubprocessEnvManager._take_step": { "total": 103.62293205100605, "count": 63411, "self": 4.585116884988565, "children": { "TorchPolicy.evaluate": { "total": 99.03781516601748, "count": 62553, "self": 99.03781516601748 } } }, "workers": { "total": 0.7857960770852515, "count": 63411, "self": 0.0, "children": { "worker_root": { "total": 1973.032132636999, "count": 63411, "is_parallel": true, "self": 833.5637494340381, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00164186600022731, "count": 1, "is_parallel": true, "self": 0.0005240100003902626, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011178559998370474, "count": 8, "is_parallel": true, "self": 0.0011178559998370474 } } }, "UnityEnvironment.step": { "total": 0.07099848899997596, "count": 1, "is_parallel": true, "self": 0.0005319359993336548, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004539760002444382, "count": 1, "is_parallel": true, "self": 0.0004539760002444382 }, "communicator.exchange": { "total": 0.06844523400013713, "count": 1, "is_parallel": true, "self": 0.06844523400013713 }, "steps_from_proto": { "total": 0.0015673430002607347, "count": 1, "is_parallel": true, "self": 0.0003682210003717046, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011991219998890301, "count": 8, "is_parallel": true, "self": 0.0011991219998890301 } } } } } } }, "UnityEnvironment.step": { "total": 1139.468383202961, "count": 63410, "is_parallel": true, "self": 30.119587097986823, "children": { "UnityEnvironment._generate_step_input": { "total": 21.950190377941453, "count": 63410, "is_parallel": true, "self": 21.950190377941453 }, "communicator.exchange": { "total": 999.2319205630306, "count": 63410, "is_parallel": true, "self": 999.2319205630306 }, "steps_from_proto": { "total": 88.16668516400205, "count": 63410, "is_parallel": true, "self": 18.470593462025136, "children": { "_process_rank_one_or_two_observation": { "total": 69.69609170197691, "count": 507280, "is_parallel": true, "self": 69.69609170197691 } } } } } } } } } } }, "trainer_advance": { "total": 612.6497549909795, "count": 63411, "self": 2.4179538219636925, "children": { "process_trajectory": { "total": 114.74795452101625, "count": 63411, "self": 114.55405293301692, "children": { "RLTrainer._checkpoint": { "total": 0.19390158799933488, "count": 2, "self": 0.19390158799933488 } } }, "_update_policy": { "total": 495.4838466479996, "count": 450, "self": 316.637119372047, "children": { "TorchPPOOptimizer.update": { "total": 178.84672727595262, "count": 22770, "self": 178.84672727595262 } } } } } } }, "trainer_threads": { "total": 9.010000212583691e-07, "count": 1, "self": 9.010000212583691e-07 }, "TrainerController._save_models": { "total": 0.09103319899986673, "count": 1, "self": 0.0014228030004233005, "children": { "RLTrainer._checkpoint": { "total": 0.08961039599944343, "count": 1, "self": 0.08961039599944343 } } } } } } }