{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4844374358654022, "min": 0.4844374358654022, "max": 1.4626991748809814, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14548.625, "min": 14548.625, "max": 44372.44140625, "count": 33 }, "Pyramids.Step.mean": { "value": 989922.0, "min": 29952.0, "max": 989922.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989922.0, "min": 29952.0, "max": 989922.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5225057005882263, "min": -0.2971446216106415, "max": 0.5507718920707703, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 146.8240966796875, "min": -70.42327880859375, "max": 154.76690673828125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005472871940582991, "min": -0.004757067188620567, "max": 0.3024058938026428, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.5378769636154175, "min": -1.2844080924987793, "max": 72.5774154663086, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06532027134588654, "min": 0.0652111707437775, "max": 0.07324379556701474, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9144837988424115, "min": 0.4916578374494298, "max": 1.0644322500424916, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01680323294844822, "min": 0.00027062356042735806, "max": 0.01680323294844822, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23524526127827508, "min": 0.0029768591647009388, "max": 0.23524526127827508, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.718518855764286e-06, "min": 7.718518855764286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001080592639807, "min": 0.0001080592639807, "max": 0.0033797054734316006, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10257280714285714, "min": 0.10257280714285714, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4360193, "min": 1.3691136000000002, "max": 2.5265684, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026702343357142856, "min": 0.00026702343357142856, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00373832807, "min": 0.00373832807, "max": 0.11268418316, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010689104907214642, "min": 0.010351241566240788, "max": 0.406168669462204, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14964747428894043, "min": 0.14491738379001617, "max": 2.8431806564331055, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 343.83720930232556, "min": 343.83720930232556, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29570.0, "min": 15984.0, "max": 32297.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5863790496490722, "min": -1.0000000521540642, "max": 1.5974092846519725, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 136.4285982698202, "min": -32.000001668930054, "max": 137.37719848006964, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5863790496490722, "min": -1.0000000521540642, "max": 1.5974092846519725, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 136.4285982698202, "min": -32.000001668930054, "max": 137.37719848006964, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03778216891331858, "min": 0.03778216891331858, "max": 8.018827424384654, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.249266526545398, "min": 3.249266526545398, "max": 128.30123879015446, "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": "1781691731", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1781694108" }, "total": 2376.7685926530003, "count": 1, "self": 0.48073778300067715, "children": { "run_training.setup": { "total": 0.03741145599997253, "count": 1, "self": 0.03741145599997253 }, "TrainerController.start_learning": { "total": 2376.2504434139996, "count": 1, "self": 1.369329333978385, "children": { "TrainerController._reset_env": { "total": 2.652903357000014, "count": 1, "self": 2.652903357000014 }, "TrainerController.advance": { "total": 2372.152803797022, "count": 63734, "self": 1.4162058960728245, "children": { "env_step": { "total": 1704.6123179129395, "count": 63734, "self": 1549.819857362906, "children": { "SubprocessEnvManager._take_step": { "total": 153.97994042697383, "count": 63734, "self": 4.706254008973701, "children": { "TorchPolicy.evaluate": { "total": 149.27368641800012, "count": 62568, "self": 149.27368641800012 } } }, "workers": { "total": 0.8125201230595849, "count": 63734, "self": 0.0, "children": { "worker_root": { "total": 2370.4492502349513, "count": 63734, "is_parallel": true, "self": 939.10941228006, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029095649999817397, "count": 1, "is_parallel": true, "self": 0.0007659600000806677, "children": { "_process_rank_one_or_two_observation": { "total": 0.002143604999901072, "count": 8, "is_parallel": true, "self": 0.002143604999901072 } } }, "UnityEnvironment.step": { "total": 0.04605088199991769, "count": 1, "is_parallel": true, "self": 0.0005466000000069471, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000528171999803817, "count": 1, "is_parallel": true, "self": 0.000528171999803817 }, "communicator.exchange": { "total": 0.04344047800009321, "count": 1, "is_parallel": true, "self": 0.04344047800009321 }, "steps_from_proto": { "total": 0.0015356320000137202, "count": 1, "is_parallel": true, "self": 0.00032978299964270263, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012058490003710176, "count": 8, "is_parallel": true, "self": 0.0012058490003710176 } } } } } } }, "UnityEnvironment.step": { "total": 1431.3398379548912, "count": 63733, "is_parallel": true, "self": 34.11497534489581, "children": { "UnityEnvironment._generate_step_input": { "total": 23.657517906056228, "count": 63733, "is_parallel": true, "self": 23.657517906056228 }, "communicator.exchange": { "total": 1264.2375593099791, "count": 63733, "is_parallel": true, "self": 1264.2375593099791 }, "steps_from_proto": { "total": 109.32978539396004, "count": 63733, "is_parallel": true, "self": 23.015591065302488, "children": { "_process_rank_one_or_two_observation": { "total": 86.31419432865755, "count": 509864, "is_parallel": true, "self": 86.31419432865755 } } } } } } } } } } }, "trainer_advance": { "total": 666.1242799880099, "count": 63734, "self": 2.6047069269864096, "children": { "process_trajectory": { "total": 125.10462803202859, "count": 63734, "self": 124.89790180302793, "children": { "RLTrainer._checkpoint": { "total": 0.20672622900065107, "count": 2, "self": 0.20672622900065107 } } }, "_update_policy": { "total": 538.4149450289949, "count": 447, "self": 296.48849648000623, "children": { "TorchPPOOptimizer.update": { "total": 241.92644854898867, "count": 22797, "self": 241.92644854898867 } } } } } } }, "trainer_threads": { "total": 8.170000000973232e-07, "count": 1, "self": 8.170000000973232e-07 }, "TrainerController._save_models": { "total": 0.07540610899923195, "count": 1, "self": 0.0012114609990021563, "children": { "RLTrainer._checkpoint": { "total": 0.07419464800022979, "count": 1, "self": 0.07419464800022979 } } } } } } }