{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.39880573749542236, "min": 0.39880573749542236, "max": 1.4926625490188599, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11900.36328125, "min": 11900.36328125, "max": 45281.41015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989921.0, "min": 29952.0, "max": 989921.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989921.0, "min": 29952.0, "max": 989921.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4262421727180481, "min": -0.10421406477689743, "max": 0.44302353262901306, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 112.5279312133789, "min": -25.219802856445312, "max": 119.6163558959961, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.03293803706765175, "min": -0.03977508842945099, "max": 0.36396950483322144, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -8.69564151763916, "min": -10.58017349243164, "max": 86.26077270507812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06996180302310534, "min": 0.0661943437187888, "max": 0.07242799068538355, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9794652423234748, "min": 0.5069903143927128, "max": 1.0220840526094168, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.011959831556252298, "min": 0.0001555012648008836, "max": 0.012783560084568072, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16743764178753218, "min": 0.00217701770721237, "max": 0.18258737967335037, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.647933165007145e-06, "min": 7.647933165007145e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010707106431010002, "min": 0.00010707106431010002, "max": 0.0035080580306474, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10254927857142858, "min": 0.10254927857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4356899, "min": 1.3886848, "max": 2.5693525999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026467292928571433, "min": 0.00026467292928571433, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003705421010000001, "min": 0.003705421010000001, "max": 0.11695832474, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007230998482555151, "min": 0.007230998482555151, "max": 0.2600422501564026, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10123398154973984, "min": 0.10123398154973984, "max": 1.820295810699463, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 466.140625, "min": 415.14666666666665, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29833.0, "min": 15984.0, "max": 32154.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.377568731084466, "min": -1.0000000521540642, "max": 1.5314986442526182, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 88.16439878940582, "min": -31.996001690626144, "max": 114.86239831894636, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.377568731084466, "min": -1.0000000521540642, "max": 1.5314986442526182, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 88.16439878940582, "min": -31.996001690626144, "max": 114.86239831894636, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03505065512001693, "min": 0.033349131696935125, "max": 4.980352709069848, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.2432419276810833, "min": 2.2432419276810833, "max": 79.68564334511757, "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": "1689807816", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1689810069" }, "total": 2253.678231109, "count": 1, "self": 0.48013048200027697, "children": { "run_training.setup": { "total": 0.03344670000001315, "count": 1, "self": 0.03344670000001315 }, "TrainerController.start_learning": { "total": 2253.164653927, "count": 1, "self": 1.4753217850111469, "children": { "TrainerController._reset_env": { "total": 4.881192850000161, "count": 1, "self": 4.881192850000161 }, "TrainerController.advance": { "total": 2246.7115652039893, "count": 63586, "self": 1.4901908109241049, "children": { "env_step": { "total": 1556.7866609980251, "count": 63586, "self": 1438.3924504290933, "children": { "SubprocessEnvManager._take_step": { "total": 117.50307888596626, "count": 63586, "self": 5.108602396949664, "children": { "TorchPolicy.evaluate": { "total": 112.3944764890166, "count": 62548, "self": 112.3944764890166 } } }, "workers": { "total": 0.8911316829655789, "count": 63586, "self": 0.0, "children": { "worker_root": { "total": 2247.513443743038, "count": 63586, "is_parallel": true, "self": 932.2391955380938, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003088498000124673, "count": 1, "is_parallel": true, "self": 0.0009563809999235673, "children": { "_process_rank_one_or_two_observation": { "total": 0.002132117000201106, "count": 8, "is_parallel": true, "self": 0.002132117000201106 } } }, "UnityEnvironment.step": { "total": 0.09517546699999002, "count": 1, "is_parallel": true, "self": 0.0006479859998762549, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047961500013116165, "count": 1, "is_parallel": true, "self": 0.00047961500013116165 }, "communicator.exchange": { "total": 0.09151479199999812, "count": 1, "is_parallel": true, "self": 0.09151479199999812 }, "steps_from_proto": { "total": 0.002533073999984481, "count": 1, "is_parallel": true, "self": 0.0006622450005124847, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018708289994719962, "count": 8, "is_parallel": true, "self": 0.0018708289994719962 } } } } } } }, "UnityEnvironment.step": { "total": 1315.2742482049441, "count": 63585, "is_parallel": true, "self": 35.53239880684373, "children": { "UnityEnvironment._generate_step_input": { "total": 24.744088307039874, "count": 63585, "is_parallel": true, "self": 24.744088307039874 }, "communicator.exchange": { "total": 1144.7853686590458, "count": 63585, "is_parallel": true, "self": 1144.7853686590458 }, "steps_from_proto": { "total": 110.21239243201467, "count": 63585, "is_parallel": true, "self": 22.647328895004875, "children": { "_process_rank_one_or_two_observation": { "total": 87.56506353700979, "count": 508680, "is_parallel": true, "self": 87.56506353700979 } } } } } } } } } } }, "trainer_advance": { "total": 688.4347133950403, "count": 63586, "self": 2.717816143060645, "children": { "process_trajectory": { "total": 120.79402282298338, "count": 63586, "self": 120.54358292898337, "children": { "RLTrainer._checkpoint": { "total": 0.2504398940000101, "count": 2, "self": 0.2504398940000101 } } }, "_update_policy": { "total": 564.9228744289962, "count": 451, "self": 367.89873800196096, "children": { "TorchPPOOptimizer.update": { "total": 197.02413642703527, "count": 22797, "self": 197.02413642703527 } } } } } } }, "trainer_threads": { "total": 9.949999366654083e-07, "count": 1, "self": 9.949999366654083e-07 }, "TrainerController._save_models": { "total": 0.09657309299973349, "count": 1, "self": 0.0015411819995279075, "children": { "RLTrainer._checkpoint": { "total": 0.09503191100020558, "count": 1, "self": 0.09503191100020558 } } } } } } }