{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5245121717453003, "min": 0.5245121717453003, "max": 1.4683809280395508, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15676.619140625, "min": 15676.619140625, "max": 44544.8046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989974.0, "min": 29952.0, "max": 989974.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989974.0, "min": 29952.0, "max": 989974.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5462453961372375, "min": -0.0893813818693161, "max": 0.5539007186889648, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 151.85621643066406, "min": -21.540912628173828, "max": 152.32269287109375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.030090928077697754, "min": 0.0053176903165876865, "max": 0.5040374398231506, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.365278244018555, "min": 1.3134695291519165, "max": 119.45687866210938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06962561037895891, "min": 0.06543960634890308, "max": 0.07392101677038451, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9747585453054248, "min": 0.4752439427639133, "max": 1.0514126868391245, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014130477420708517, "min": 0.0006469925694302089, "max": 0.015236421878498047, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19782668388991925, "min": 0.007763910833162507, "max": 0.21330990629897265, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.446461803592854e-06, "min": 7.446461803592854e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010425046525029996, "min": 0.00010425046525029996, "max": 0.0035076809307730992, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248212142857142, "min": 0.10248212142857142, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347497, "min": 1.3886848, "max": 2.6176047000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025796393071428564, "min": 0.00025796393071428564, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036114950299999987, "min": 0.0036114950299999987, "max": 0.11694576731, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010309159755706787, "min": 0.010206242091953754, "max": 0.5324414372444153, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14432823657989502, "min": 0.14288738369941711, "max": 3.7270898818969727, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 346.775, "min": 346.775, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27742.0, "min": 15984.0, "max": 32633.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6282224778085947, "min": -1.0000000521540642, "max": 1.6282224778085947, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 130.25779822468758, "min": -30.665001675486565, "max": 142.41539785265923, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6282224778085947, "min": -1.0000000521540642, "max": 1.6282224778085947, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 130.25779822468758, "min": -30.665001675486565, "max": 142.41539785265923, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03690245527232037, "min": 0.03690245527232037, "max": 11.691608242690563, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9521964217856294, "min": 2.9521964217856294, "max": 187.065731883049, "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": "1717183678", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717185954" }, "total": 2275.489956409, "count": 1, "self": 0.5888061000000562, "children": { "run_training.setup": { "total": 0.08367152700020597, "count": 1, "self": 0.08367152700020597 }, "TrainerController.start_learning": { "total": 2274.817478782, "count": 1, "self": 1.538024738981676, "children": { "TrainerController._reset_env": { "total": 2.7331542339998123, "count": 1, "self": 2.7331542339998123 }, "TrainerController.advance": { "total": 2270.450689360018, "count": 63913, "self": 1.5674759250487114, "children": { "env_step": { "total": 1620.7483550599673, "count": 63913, "self": 1481.048849954071, "children": { "SubprocessEnvManager._take_step": { "total": 138.7712550989204, "count": 63913, "self": 4.944066397851657, "children": { "TorchPolicy.evaluate": { "total": 133.82718870106874, "count": 62548, "self": 133.82718870106874 } } }, "workers": { "total": 0.9282500069757589, "count": 63913, "self": 0.0, "children": { "worker_root": { "total": 2269.5709389880076, "count": 63913, "is_parallel": true, "self": 920.9424124769994, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002737472999797319, "count": 1, "is_parallel": true, "self": 0.00073389799990764, "children": { "_process_rank_one_or_two_observation": { "total": 0.002003574999889679, "count": 8, "is_parallel": true, "self": 0.002003574999889679 } } }, "UnityEnvironment.step": { "total": 0.04954141400003209, "count": 1, "is_parallel": true, "self": 0.0006079439999666647, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004395400001158123, "count": 1, "is_parallel": true, "self": 0.0004395400001158123 }, "communicator.exchange": { "total": 0.04684194399987973, "count": 1, "is_parallel": true, "self": 0.04684194399987973 }, "steps_from_proto": { "total": 0.0016519860000698827, "count": 1, "is_parallel": true, "self": 0.0003357330010658188, "children": { "_process_rank_one_or_two_observation": { "total": 0.001316252999004064, "count": 8, "is_parallel": true, "self": 0.001316252999004064 } } } } } } }, "UnityEnvironment.step": { "total": 1348.6285265110082, "count": 63912, "is_parallel": true, "self": 34.89706483396503, "children": { "UnityEnvironment._generate_step_input": { "total": 24.33059817400681, "count": 63912, "is_parallel": true, "self": 24.33059817400681 }, "communicator.exchange": { "total": 1185.3089984420017, "count": 63912, "is_parallel": true, "self": 1185.3089984420017 }, "steps_from_proto": { "total": 104.0918650610347, "count": 63912, "is_parallel": true, "self": 21.837636461088096, "children": { "_process_rank_one_or_two_observation": { "total": 82.2542285999466, "count": 511296, "is_parallel": true, "self": 82.2542285999466 } } } } } } } } } } }, "trainer_advance": { "total": 648.1348583750018, "count": 63913, "self": 2.8002164059676034, "children": { "process_trajectory": { "total": 134.42033066303338, "count": 63913, "self": 134.16502085903312, "children": { "RLTrainer._checkpoint": { "total": 0.2553098040002624, "count": 2, "self": 0.2553098040002624 } } }, "_update_policy": { "total": 510.91431130600085, "count": 451, "self": 304.887499234972, "children": { "TorchPPOOptimizer.update": { "total": 206.02681207102887, "count": 22785, "self": 206.02681207102887 } } } } } } }, "trainer_threads": { "total": 1.4060005923965946e-06, "count": 1, "self": 1.4060005923965946e-06 }, "TrainerController._save_models": { "total": 0.09560904299996764, "count": 1, "self": 0.0014479080000455724, "children": { "RLTrainer._checkpoint": { "total": 0.09416113499992207, "count": 1, "self": 0.09416113499992207 } } } } } } }