{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7728339433670044, "min": 0.7288958430290222, "max": 1.4431042671203613, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 23061.365234375, "min": 22041.810546875, "max": 43778.01171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989888.0, "min": 29952.0, "max": 989888.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989888.0, "min": 29952.0, "max": 989888.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.36542537808418274, "min": -0.09728502482175827, "max": 0.40090176463127136, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 96.10687255859375, "min": -23.348405838012695, "max": 106.23896789550781, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -1.1882383823394775, "min": -1.2912342548370361, "max": 0.4022040367126465, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -312.5066833496094, "min": -339.5946044921875, "max": 95.32235717773438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06886661891032765, "min": 0.06353791788610415, "max": 0.07306156648018532, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.964132664744587, "min": 0.48965808772816505, "max": 1.0783730125986042, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.11593608859749065, "min": 0.0003412878394557795, "max": 0.18283836018142133, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 1.6231052403648691, "min": 0.0037541662340135743, "max": 2.5597370425398984, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.487947504050002e-06, "min": 7.487947504050002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010483126505670003, "min": 0.00010483126505670003, "max": 0.0035074124308626, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249595000000002, "min": 0.10249595000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349433000000003, "min": 1.3886848, "max": 2.5691374, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002593454050000001, "min": 0.0002593454050000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036308356700000015, "min": 0.0036308356700000015, "max": 0.11693682626, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012907558120787144, "min": 0.012907558120787144, "max": 0.5343934893608093, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18070581555366516, "min": 0.18070581555366516, "max": 3.7407546043395996, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 449.3333333333333, "min": 426.8857142857143, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 26960.0, "min": 15984.0, "max": 33105.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3506199823071559, "min": -1.0000000521540642, "max": 1.4373104195319004, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 81.03719893842936, "min": -31.998401656746864, "max": 98.1143981590867, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3506199823071559, "min": -1.0000000521540642, "max": 1.4373104195319004, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 81.03719893842936, "min": -31.998401656746864, "max": 98.1143981590867, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06115137994347606, "min": 0.06115137994347606, "max": 10.732672781683505, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6690827966085635, "min": 3.6690827966085635, "max": 171.72276450693607, "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": "1681616572", "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": "1681618607" }, "total": 2035.3231744579998, "count": 1, "self": 0.483669524999641, "children": { "run_training.setup": { "total": 0.16537102200004483, "count": 1, "self": 0.16537102200004483 }, "TrainerController.start_learning": { "total": 2034.6741339110001, "count": 1, "self": 1.3600846060178355, "children": { "TrainerController._reset_env": { "total": 4.598943123000026, "count": 1, "self": 4.598943123000026 }, "TrainerController.advance": { "total": 2028.6194591779822, "count": 63493, "self": 1.425455484955819, "children": { "env_step": { "total": 1423.9107883219754, "count": 63493, "self": 1317.812411175018, "children": { "SubprocessEnvManager._take_step": { "total": 105.29021417598346, "count": 63493, "self": 4.6252681989556095, "children": { "TorchPolicy.evaluate": { "total": 100.66494597702786, "count": 62575, "self": 100.66494597702786 } } }, "workers": { "total": 0.8081629709738536, "count": 63493, "self": 0.0, "children": { "worker_root": { "total": 2029.9861528689992, "count": 63493, "is_parallel": true, "self": 818.419670138964, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024876270001641387, "count": 1, "is_parallel": true, "self": 0.0007285760000286245, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017590510001355142, "count": 8, "is_parallel": true, "self": 0.0017590510001355142 } } }, "UnityEnvironment.step": { "total": 0.04810289199986073, "count": 1, "is_parallel": true, "self": 0.0005465739998271602, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005396659998950781, "count": 1, "is_parallel": true, "self": 0.0005396659998950781 }, "communicator.exchange": { "total": 0.045347320000018954, "count": 1, "is_parallel": true, "self": 0.045347320000018954 }, "steps_from_proto": { "total": 0.0016693320001195389, "count": 1, "is_parallel": true, "self": 0.0003833470004792616, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012859849996402772, "count": 8, "is_parallel": true, "self": 0.0012859849996402772 } } } } } } }, "UnityEnvironment.step": { "total": 1211.5664827300352, "count": 63492, "is_parallel": true, "self": 31.91617613206199, "children": { "UnityEnvironment._generate_step_input": { "total": 22.3511165320499, "count": 63492, "is_parallel": true, "self": 22.3511165320499 }, "communicator.exchange": { "total": 1065.9626659239543, "count": 63492, "is_parallel": true, "self": 1065.9626659239543 }, "steps_from_proto": { "total": 91.336524141969, "count": 63492, "is_parallel": true, "self": 19.319582486094987, "children": { "_process_rank_one_or_two_observation": { "total": 72.016941655874, "count": 507936, "is_parallel": true, "self": 72.016941655874 } } } } } } } } } } }, "trainer_advance": { "total": 603.283215371051, "count": 63493, "self": 2.516635445034808, "children": { "process_trajectory": { "total": 100.32794902201113, "count": 63493, "self": 100.12603214601177, "children": { "RLTrainer._checkpoint": { "total": 0.20191687599935904, "count": 2, "self": 0.20191687599935904 } } }, "_update_policy": { "total": 500.4386309040051, "count": 449, "self": 319.65342836502236, "children": { "TorchPPOOptimizer.update": { "total": 180.78520253898273, "count": 22773, "self": 180.78520253898273 } } } } } } }, "trainer_threads": { "total": 1.0750000001280569e-06, "count": 1, "self": 1.0750000001280569e-06 }, "TrainerController._save_models": { "total": 0.09564592900005664, "count": 1, "self": 0.0015283780003301217, "children": { "RLTrainer._checkpoint": { "total": 0.09411755099972652, "count": 1, "self": 0.09411755099972652 } } } } } } }