{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3293026089668274, "min": 0.3293026089668274, "max": 1.4768606424331665, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9984.455078125, "min": 9960.220703125, "max": 44802.04296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989953.0, "min": 29919.0, "max": 989953.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989953.0, "min": 29919.0, "max": 989953.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6807458996772766, "min": -0.11291810870170593, "max": 0.6956156492233276, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 199.45855712890625, "min": -27.100345611572266, "max": 199.64169311523438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04961402714252472, "min": -0.014137963764369488, "max": 0.1505739986896515, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 14.536910057067871, "min": -3.8455262184143066, "max": 36.137760162353516, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07065629516728222, "min": 0.06428403452360619, "max": 0.07517236023254337, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0598444275092334, "min": 0.5587014584105698, "max": 1.0633926029812417, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015328271364948402, "min": 0.001292096462728602, "max": 0.0170109942590075, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22992407047422603, "min": 0.013948420285406308, "max": 0.24627738200554936, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.54045748654667e-06, "min": 7.54045748654667e-06, "max": 0.0002948437142187625, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011310686229820006, "min": 0.00011310686229820006, "max": 0.0035083391305536994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251345333333334, "min": 0.10251345333333334, "max": 0.1982812375, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377018, "min": 1.4780932, "max": 2.5694462999999996, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002610939880000002, "min": 0.0002610939880000002, "max": 0.00982829562625, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003916409820000003, "min": 0.003916409820000003, "max": 0.11696768537000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010718907229602337, "min": 0.010718907229602337, "max": 0.35783645510673523, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16078360378742218, "min": 0.15546579658985138, "max": 2.862691640853882, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 282.4, "min": 277.57547169811323, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31064.0, "min": 16462.0, "max": 32545.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6630363504317673, "min": -0.999962551984936, "max": 1.6800978992444773, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 182.9339985474944, "min": -31.998801663517952, "max": 182.9339985474944, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6630363504317673, "min": -0.999962551984936, "max": 1.6800978992444773, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 182.9339985474944, "min": -31.998801663517952, "max": 182.9339985474944, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03146121728271034, "min": 0.03146121728271034, "max": 7.288936883211136, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4607339010981377, "min": 3.3031566040590405, "max": 123.91192701458931, "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": "1739933355", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739935637" }, "total": 2281.6220935049996, "count": 1, "self": 0.4755566000003455, "children": { "run_training.setup": { "total": 0.01990539199982777, "count": 1, "self": 0.01990539199982777 }, "TrainerController.start_learning": { "total": 2281.1266315129997, "count": 1, "self": 1.4433197819525958, "children": { "TrainerController._reset_env": { "total": 2.707528168999943, "count": 1, "self": 2.707528168999943 }, "TrainerController.advance": { "total": 2276.8808057770475, "count": 64164, "self": 1.3643893660473623, "children": { "env_step": { "total": 1605.9137789170425, "count": 64164, "self": 1451.9239104951048, "children": { "SubprocessEnvManager._take_step": { "total": 153.20008128395784, "count": 64164, "self": 4.60915476394166, "children": { "TorchPolicy.evaluate": { "total": 148.59092652001618, "count": 62556, "self": 148.59092652001618 } } }, "workers": { "total": 0.7897871379798289, "count": 64164, "self": 0.0, "children": { "worker_root": { "total": 2276.079204983125, "count": 64164, "is_parallel": true, "self": 936.771817467049, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002433612999993784, "count": 1, "is_parallel": true, "self": 0.0007339710000451305, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016996419999486534, "count": 8, "is_parallel": true, "self": 0.0016996419999486534 } } }, "UnityEnvironment.step": { "total": 0.07796667299999172, "count": 1, "is_parallel": true, "self": 0.0005459509998217982, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000461236000091958, "count": 1, "is_parallel": true, "self": 0.000461236000091958 }, "communicator.exchange": { "total": 0.07439828099995793, "count": 1, "is_parallel": true, "self": 0.07439828099995793 }, "steps_from_proto": { "total": 0.002561205000120026, "count": 1, "is_parallel": true, "self": 0.0012245190002886375, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013366859998313885, "count": 8, "is_parallel": true, "self": 0.0013366859998313885 } } } } } } }, "UnityEnvironment.step": { "total": 1339.3073875160758, "count": 64163, "is_parallel": true, "self": 31.25430914391268, "children": { "UnityEnvironment._generate_step_input": { "total": 22.978786583011697, "count": 64163, "is_parallel": true, "self": 22.978786583011697 }, "communicator.exchange": { "total": 1188.5421302110633, "count": 64163, "is_parallel": true, "self": 1188.5421302110633 }, "steps_from_proto": { "total": 96.53216157808811, "count": 64163, "is_parallel": true, "self": 19.420860071395737, "children": { "_process_rank_one_or_two_observation": { "total": 77.11130150669237, "count": 513304, "is_parallel": true, "self": 77.11130150669237 } } } } } } } } } } }, "trainer_advance": { "total": 669.6026374939574, "count": 64164, "self": 2.6443425600430146, "children": { "process_trajectory": { "total": 127.33983188491061, "count": 64164, "self": 127.08893747191064, "children": { "RLTrainer._checkpoint": { "total": 0.25089441299996906, "count": 2, "self": 0.25089441299996906 } } }, "_update_policy": { "total": 539.6184630490038, "count": 453, "self": 297.06318977402907, "children": { "TorchPPOOptimizer.update": { "total": 242.55527327497475, "count": 22764, "self": 242.55527327497475 } } } } } } }, "trainer_threads": { "total": 9.479999789618887e-07, "count": 1, "self": 9.479999789618887e-07 }, "TrainerController._save_models": { "total": 0.0949768369996491, "count": 1, "self": 0.0013938839997535979, "children": { "RLTrainer._checkpoint": { "total": 0.0935829529998955, "count": 1, "self": 0.0935829529998955 } } } } } } }