{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.47824469208717346, "min": 0.47824469208717346, "max": 1.4493423700332642, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14270.8212890625, "min": 14270.8212890625, "max": 43967.25, "count": 33 }, "Pyramids.Step.mean": { "value": 989896.0, "min": 29938.0, "max": 989896.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989896.0, "min": 29938.0, "max": 989896.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.42649492621421814, "min": -0.10173536837100983, "max": 0.5256990194320679, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 115.15363311767578, "min": -24.416488647460938, "max": 144.04153442382812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009741313755512238, "min": -0.013773174956440926, "max": 0.2964588403701782, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.630154609680176, "min": -3.5810256004333496, "max": 70.2607421875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06478934182091035, "min": 0.06478934182091035, "max": 0.07342707097018583, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.907050785492745, "min": 0.5572040628764412, "max": 1.060075694649462, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014427138266889955, "min": 0.001042014054790723, "max": 0.01676017729466369, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20197993573645937, "min": 0.012504168657488676, "max": 0.23464248212529165, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.320890416878574e-06, "min": 7.320890416878574e-06, "max": 0.00029501572666142497, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010249246583630004, "min": 0.00010249246583630004, "max": 0.003632835189055, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024402642857143, "min": 0.1024402642857143, "max": 0.198338575, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4341637000000003, "min": 1.4341637000000003, "max": 2.6173737000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025378240214285724, "min": 0.00025378240214285724, "max": 0.0098340236425, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035529536300000016, "min": 0.0035529536300000016, "max": 0.12111340550000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008871405385434628, "min": 0.008871405385434628, "max": 0.3282895088195801, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12419967353343964, "min": 0.12419967353343964, "max": 2.6263160705566406, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 414.36486486486484, "min": 354.7529411764706, "max": 992.8709677419355, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30663.0, "min": 16865.0, "max": 32503.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4234324118776902, "min": -0.9181313009466976, "max": 1.5680026458700498, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 105.33399847894907, "min": -29.380201630294323, "max": 131.84459805488586, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4234324118776902, "min": -0.9181313009466976, "max": 1.5680026458700498, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 105.33399847894907, "min": -29.380201630294323, "max": 131.84459805488586, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03847581556820424, "min": 0.03726603470970397, "max": 6.505901773186291, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8472103520471137, "min": 2.8167578261636663, "max": 110.60033014416695, "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": "1679450314", "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": "1679452370" }, "total": 2055.828147861, "count": 1, "self": 0.7784286549999706, "children": { "run_training.setup": { "total": 0.10755296100001033, "count": 1, "self": 0.10755296100001033 }, "TrainerController.start_learning": { "total": 2054.942166245, "count": 1, "self": 1.3136951349742958, "children": { "TrainerController._reset_env": { "total": 5.897364628000105, "count": 1, "self": 5.897364628000105 }, "TrainerController.advance": { "total": 2047.5900715570258, "count": 63779, "self": 1.3609208679527, "children": { "env_step": { "total": 1431.4868217461083, "count": 63779, "self": 1326.4106330051807, "children": { "SubprocessEnvManager._take_step": { "total": 104.29980116595902, "count": 63779, "self": 4.605973200931885, "children": { "TorchPolicy.evaluate": { "total": 99.69382796502714, "count": 62556, "self": 99.69382796502714 } } }, "workers": { "total": 0.7763875749685667, "count": 63779, "self": 0.0, "children": { "worker_root": { "total": 2050.425384598091, "count": 63779, "is_parallel": true, "self": 834.0379390850871, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017826030000378523, "count": 1, "is_parallel": true, "self": 0.0005576420001034421, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012249609999344102, "count": 8, "is_parallel": true, "self": 0.0012249609999344102 } } }, "UnityEnvironment.step": { "total": 0.04708113400010916, "count": 1, "is_parallel": true, "self": 0.0005008540003927919, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005015889998958301, "count": 1, "is_parallel": true, "self": 0.0005015889998958301 }, "communicator.exchange": { "total": 0.04440864499997588, "count": 1, "is_parallel": true, "self": 0.04440864499997588 }, "steps_from_proto": { "total": 0.0016700459998446604, "count": 1, "is_parallel": true, "self": 0.0003563129994290648, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013137330004155956, "count": 8, "is_parallel": true, "self": 0.0013137330004155956 } } } } } } }, "UnityEnvironment.step": { "total": 1216.387445513004, "count": 63778, "is_parallel": true, "self": 30.222323572985715, "children": { "UnityEnvironment._generate_step_input": { "total": 23.089575577046162, "count": 63778, "is_parallel": true, "self": 23.089575577046162 }, "communicator.exchange": { "total": 1073.9946647799975, "count": 63778, "is_parallel": true, "self": 1073.9946647799975 }, "steps_from_proto": { "total": 89.0808815829746, "count": 63778, "is_parallel": true, "self": 18.785962323866897, "children": { "_process_rank_one_or_two_observation": { "total": 70.2949192591077, "count": 510224, "is_parallel": true, "self": 70.2949192591077 } } } } } } } } } } }, "trainer_advance": { "total": 614.7423289429648, "count": 63779, "self": 2.5245584070084988, "children": { "process_trajectory": { "total": 115.89321274996018, "count": 63779, "self": 115.58397001795993, "children": { "RLTrainer._checkpoint": { "total": 0.3092427320002571, "count": 2, "self": 0.3092427320002571 } } }, "_update_policy": { "total": 496.32455778599615, "count": 457, "self": 313.7214556410436, "children": { "TorchPPOOptimizer.update": { "total": 182.60310214495257, "count": 22836, "self": 182.60310214495257 } } } } } } }, "trainer_threads": { "total": 1.1409997568989638e-06, "count": 1, "self": 1.1409997568989638e-06 }, "TrainerController._save_models": { "total": 0.14103378399977373, "count": 1, "self": 0.0020523449998108845, "children": { "RLTrainer._checkpoint": { "total": 0.13898143899996285, "count": 1, "self": 0.13898143899996285 } } } } } } }