{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4530212879180908, "min": 0.4530212879180908, "max": 1.4745392799377441, "count": 28 }, "Pyramids.Policy.Entropy.sum": { "value": 13612.3837890625, "min": 13612.3837890625, "max": 44731.625, "count": 28 }, "Pyramids.Step.mean": { "value": 839929.0, "min": 29923.0, "max": 839929.0, "count": 28 }, "Pyramids.Step.sum": { "value": 839929.0, "min": 29923.0, "max": 839929.0, "count": 28 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6553109884262085, "min": -0.10782083868980408, "max": 0.6553109884262085, "count": 28 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 185.4530029296875, "min": -26.09264373779297, "max": 185.4530029296875, "count": 28 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.015051504597067833, "min": -0.027884522452950478, "max": 0.39482107758522034, "count": 28 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -4.259575843811035, "min": -7.61247444152832, "max": 93.57259368896484, "count": 28 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07133219251686354, "min": 0.06629738234221891, "max": 0.07448596894253223, "count": 28 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9986506952360895, "min": 0.614651782770272, "max": 1.0921571219417576, "count": 28 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014269942190453763, "min": 0.000417585136017765, "max": 0.016432991460074903, "count": 28 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1997791906663527, "min": 0.00501102163221318, "max": 0.20924611313751446, "count": 28 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.0002174927846452714, "min": 0.0002174927846452714, "max": 0.0002982635783565851, "count": 28 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0030448989850337996, "min": 0.0026843722052092662, "max": 0.004162607312464267, "count": 28 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1724975857142857, "min": 0.1724975857142857, "max": 0.1994211925925926, "count": 28 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.4149662, "min": 1.7947907333333335, "max": 2.8875357333333334, "count": 28 }, "Pyramids.Policy.Beta.mean": { "value": 0.007252508812857142, "min": 0.007252508812857142, "max": 0.009942177140000001, "count": 28 }, "Pyramids.Policy.Beta.sum": { "value": 0.10153512338, "min": 0.08947959426000002, "max": 0.13876481976000002, "count": 28 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009404017589986324, "min": 0.009403275325894356, "max": 0.44545331597328186, "count": 28 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1316562443971634, "min": 0.13164585828781128, "max": 4.009079933166504, "count": 28 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 285.3009708737864, "min": 285.3009708737864, "max": 991.1764705882352, "count": 28 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29386.0, "min": 16850.0, "max": 33931.0, "count": 28 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6952795885430956, "min": -0.9265394445621606, "max": 1.6952795885430956, "count": 28 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 174.61379761993885, "min": -30.5758016705513, "max": 174.61379761993885, "count": 28 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6952795885430956, "min": -0.9265394445621606, "max": 1.6952795885430956, "count": 28 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 174.61379761993885, "min": -30.5758016705513, "max": 174.61379761993885, "count": 28 }, "Pyramids.Policy.RndReward.mean": { "value": 0.027941982839674716, "min": 0.027941982839674716, "max": 10.727661699056625, "count": 28 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8780242324864957, "min": 2.7949321906198747, "max": 182.37024888396263, "count": 28 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 28 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 28 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684981242", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684983173" }, "total": 1931.593726478, "count": 1, "self": 0.5274269509998248, "children": { "run_training.setup": { "total": 0.04259902300009344, "count": 1, "self": 0.04259902300009344 }, "TrainerController.start_learning": { "total": 1931.023700504, "count": 1, "self": 1.1416421229835123, "children": { "TrainerController._reset_env": { "total": 3.9345341390001067, "count": 1, "self": 3.9345341390001067 }, "TrainerController.advance": { "total": 1925.9462294010166, "count": 54952, "self": 1.1571584419650662, "children": { "env_step": { "total": 1366.6647152060104, "count": 54952, "self": 1273.0030594940122, "children": { "SubprocessEnvManager._take_step": { "total": 92.9809465459798, "count": 54952, "self": 4.089458481962765, "children": { "TorchPolicy.evaluate": { "total": 88.89148806401704, "count": 53725, "self": 88.89148806401704 } } }, "workers": { "total": 0.6807091660184597, "count": 54951, "self": 0.0, "children": { "worker_root": { "total": 1926.7442980209464, "count": 54951, "is_parallel": true, "self": 751.218667466914, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018132830000467948, "count": 1, "is_parallel": true, "self": 0.0005797229996460374, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012335600004007574, "count": 8, "is_parallel": true, "self": 0.0012335600004007574 } } }, "UnityEnvironment.step": { "total": 0.047585327999968285, "count": 1, "is_parallel": true, "self": 0.0005638200000248617, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005202790000566893, "count": 1, "is_parallel": true, "self": 0.0005202790000566893 }, "communicator.exchange": { "total": 0.044637645999955566, "count": 1, "is_parallel": true, "self": 0.044637645999955566 }, "steps_from_proto": { "total": 0.0018635829999311682, "count": 1, "is_parallel": true, "self": 0.00039176299992504937, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014718200000061188, "count": 8, "is_parallel": true, "self": 0.0014718200000061188 } } } } } } }, "UnityEnvironment.step": { "total": 1175.5256305540324, "count": 54950, "is_parallel": true, "self": 27.44596810098642, "children": { "UnityEnvironment._generate_step_input": { "total": 19.481681209019598, "count": 54950, "is_parallel": true, "self": 19.481681209019598 }, "communicator.exchange": { "total": 1044.8769958690586, "count": 54950, "is_parallel": true, "self": 1044.8769958690586 }, "steps_from_proto": { "total": 83.72098537496777, "count": 54950, "is_parallel": true, "self": 16.89457854696684, "children": { "_process_rank_one_or_two_observation": { "total": 66.82640682800093, "count": 439600, "is_parallel": true, "self": 66.82640682800093 } } } } } } } } } } }, "trainer_advance": { "total": 558.1243557530411, "count": 54951, "self": 2.2870294229937826, "children": { "process_trajectory": { "total": 93.29248101004737, "count": 54951, "self": 93.14386159304763, "children": { "RLTrainer._checkpoint": { "total": 0.14861941699973613, "count": 1, "self": 0.14861941699973613 } } }, "_update_policy": { "total": 462.5448453199999, "count": 394, "self": 300.76553456998704, "children": { "TorchPPOOptimizer.update": { "total": 161.77931075001288, "count": 19581, "self": 161.77931075001288 } } } } } } }, "trainer_threads": { "total": 1.3180001587898005e-06, "count": 1, "self": 1.3180001587898005e-06 }, "TrainerController._save_models": { "total": 0.001293522999731067, "count": 1, "self": 2.678099963304703e-05, "children": { "RLTrainer._checkpoint": { "total": 0.00126674200009802, "count": 1, "self": 0.00126674200009802 } } } } } } }