{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5990259647369385, "min": 0.5738786458969116, "max": 1.4947173595428467, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17932.44140625, "min": 17188.8125, "max": 45343.74609375, "count": 33 }, "Pyramids.Step.mean": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3643811345100403, "min": -0.10971350967884064, "max": 0.3643811345100403, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 96.92538452148438, "min": -26.440956115722656, "max": 96.92538452148438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.4211813509464264, "min": -0.21764744818210602, "max": 0.4211813509464264, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 112.03424072265625, "min": -57.02363204956055, "max": 112.03424072265625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06817483065588888, "min": 0.06521761433726193, "max": 0.07470178645244098, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9544476291824443, "min": 0.5229125051670869, "max": 1.0386050079153695, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.03747266963316996, "min": 0.00010662233936261992, "max": 0.03747266963316996, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.5246173748643794, "min": 0.001386090411714059, "max": 0.5246173748643794, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.530761775492858e-06, "min": 7.530761775492858e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010543066485690002, "min": 0.00010543066485690002, "max": 0.003331121789626099, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251022142857145, "min": 0.10251022142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351431000000003, "min": 1.3886848, "max": 2.4006383000000007, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002607711207142858, "min": 0.0002607711207142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036507956900000012, "min": 0.0036507956900000012, "max": 0.11104635261000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010880030691623688, "min": 0.010880030691623688, "max": 0.43722057342529297, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15232042968273163, "min": 0.15232042968273163, "max": 3.060544013977051, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 481.0, "min": 481.0, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30303.0, "min": 15984.0, "max": 33789.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3602031527294054, "min": -1.0000000521540642, "max": 1.3602031527294054, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 85.69279862195253, "min": -31.997201666235924, "max": 85.69279862195253, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3602031527294054, "min": -1.0000000521540642, "max": 1.3602031527294054, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 85.69279862195253, "min": -31.997201666235924, "max": 85.69279862195253, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05347130073895973, "min": 0.05347130073895973, "max": 10.397559150122106, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3686919465544634, "min": 3.2627781379851513, "max": 166.3609464019537, "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": "1747811855", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1747813951" }, "total": 2095.6671436160004, "count": 1, "self": 0.48857348500041553, "children": { "run_training.setup": { "total": 0.021951539999918168, "count": 1, "self": 0.021951539999918168 }, "TrainerController.start_learning": { "total": 2095.156618591, "count": 1, "self": 1.2730057210114865, "children": { "TrainerController._reset_env": { "total": 2.3113080010002705, "count": 1, "self": 2.3113080010002705 }, "TrainerController.advance": { "total": 2091.493746907988, "count": 63355, "self": 1.3232204248565722, "children": { "env_step": { "total": 1429.3983528701237, "count": 63355, "self": 1285.0563300699846, "children": { "SubprocessEnvManager._take_step": { "total": 143.62380487707514, "count": 63355, "self": 4.420565302018076, "children": { "TorchPolicy.evaluate": { "total": 139.20323957505707, "count": 62571, "self": 139.20323957505707 } } }, "workers": { "total": 0.7182179230640031, "count": 63355, "self": 0.0, "children": { "worker_root": { "total": 2090.345788091123, "count": 63355, "is_parallel": true, "self": 909.6278986391176, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001932553999722586, "count": 1, "is_parallel": true, "self": 0.0006222689989954233, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013102850007271627, "count": 8, "is_parallel": true, "self": 0.0013102850007271627 } } }, "UnityEnvironment.step": { "total": 0.058019252000121924, "count": 1, "is_parallel": true, "self": 0.0005274710001685889, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043988900006297627, "count": 1, "is_parallel": true, "self": 0.00043988900006297627 }, "communicator.exchange": { "total": 0.05548894000003202, "count": 1, "is_parallel": true, "self": 0.05548894000003202 }, "steps_from_proto": { "total": 0.0015629519998583419, "count": 1, "is_parallel": true, "self": 0.0003536939998411981, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012092580000171438, "count": 8, "is_parallel": true, "self": 0.0012092580000171438 } } } } } } }, "UnityEnvironment.step": { "total": 1180.7178894520052, "count": 63354, "is_parallel": true, "self": 31.016242053860424, "children": { "UnityEnvironment._generate_step_input": { "total": 22.481824866967145, "count": 63354, "is_parallel": true, "self": 22.481824866967145 }, "communicator.exchange": { "total": 1036.2249648089673, "count": 63354, "is_parallel": true, "self": 1036.2249648089673 }, "steps_from_proto": { "total": 90.99485772221033, "count": 63354, "is_parallel": true, "self": 17.99262845491603, "children": { "_process_rank_one_or_two_observation": { "total": 73.0022292672943, "count": 506832, "is_parallel": true, "self": 73.0022292672943 } } } } } } } } } } }, "trainer_advance": { "total": 660.7721736130079, "count": 63355, "self": 2.4216517270410804, "children": { "process_trajectory": { "total": 122.45976789397355, "count": 63355, "self": 122.26085898097426, "children": { "RLTrainer._checkpoint": { "total": 0.19890891299928626, "count": 2, "self": 0.19890891299928626 } } }, "_update_policy": { "total": 535.8907539919933, "count": 445, "self": 298.4387710920046, "children": { "TorchPPOOptimizer.update": { "total": 237.4519828999887, "count": 22788, "self": 237.4519828999887 } } } } } } }, "trainer_threads": { "total": 9.030000001075678e-07, "count": 1, "self": 9.030000001075678e-07 }, "TrainerController._save_models": { "total": 0.07855705800011492, "count": 1, "self": 0.0011738399998648674, "children": { "RLTrainer._checkpoint": { "total": 0.07738321800025005, "count": 1, "self": 0.07738321800025005 } } } } } } }