{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41431453824043274, "min": 0.41431453824043274, "max": 1.4875783920288086, "count": 35 }, "Pyramids.Policy.Entropy.sum": { "value": 12409.548828125, "min": 12409.548828125, "max": 45127.1796875, "count": 35 }, "Pyramids.Step.mean": { "value": 1049896.0, "min": 29952.0, "max": 1049896.0, "count": 35 }, "Pyramids.Step.sum": { "value": 1049896.0, "min": 29952.0, "max": 1049896.0, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6361086368560791, "min": -0.09613387286663055, "max": 0.6844275593757629, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 179.38262939453125, "min": -23.168262481689453, "max": 195.06185913085938, "count": 35 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.020924950018525124, "min": -0.008953395299613476, "max": 0.34008076786994934, "count": 35 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.900835990905762, "min": -2.381603240966797, "max": 81.619384765625, "count": 35 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0693876647835298, "min": 0.06504483297109344, "max": 0.0740363945578449, "count": 35 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9714273069694173, "min": 0.5182547619049143, "max": 1.0757602347293866, "count": 35 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014152369277282905, "min": 0.000579101062018167, "max": 0.01590985846373119, "count": 35 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19813316988196067, "min": 0.006949212744218005, "max": 0.22273801849223668, "count": 35 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019654792019832383, "min": 0.00019654792019832383, "max": 0.00029838354339596195, "count": 35 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0027516708827765336, "min": 0.0020886848037717336, "max": 0.003969062276979266, "count": 35 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1655159619047619, "min": 0.1655159619047619, "max": 0.19946118095238097, "count": 35 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3172234666666665, "min": 1.3962282666666668, "max": 2.782510333333334, "count": 35 }, "Pyramids.Policy.Beta.mean": { "value": 0.006555044594285714, "min": 0.006555044594285714, "max": 0.009946171977142856, "count": 35 }, "Pyramids.Policy.Beta.sum": { "value": 0.09177062432, "min": 0.06962320384, "max": 0.13230977126, "count": 35 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010334077291190624, "min": 0.010334077291190624, "max": 0.44211840629577637, "count": 35 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1446770876646042, "min": 0.1446770876646042, "max": 3.0948288440704346, "count": 35 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 290.46, "min": 278.462962962963, "max": 999.0, "count": 35 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29046.0, "min": 15984.0, "max": 33696.0, "count": 35 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6495179866999388, "min": -1.0000000521540642, "max": 1.72221099209348, "count": 35 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 164.95179866999388, "min": -30.766001746058464, "max": 187.72099813818932, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6495179866999388, "min": -1.0000000521540642, "max": 1.72221099209348, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 164.95179866999388, "min": -30.766001746058464, "max": 187.72099813818932, "count": 35 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031825694876606574, "min": 0.03177953367372505, "max": 9.404450627043843, "count": 35 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1825694876606576, "min": 3.1825694876606576, "max": 150.4712100327015, "count": 35 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1761236797", "python_version": "3.10.13 (main, Oct 14 2025, 13:44:10) [GCC 14.2.0]", "command_line_arguments": "/home/chames/mlagents/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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1761238742" }, "total": 1945.0472237729996, "count": 1, "self": 0.16114953200030868, "children": { "run_training.setup": { "total": 0.02763485799960108, "count": 1, "self": 0.02763485799960108 }, "TrainerController.start_learning": { "total": 1944.8584393829997, "count": 1, "self": 1.235537349045444, "children": { "TrainerController._reset_env": { "total": 1.8660640100001729, "count": 1, "self": 1.8660640100001729 }, "TrainerController.advance": { "total": 1941.6465538159541, "count": 67434, "self": 1.2579140690399981, "children": { "env_step": { "total": 1225.6884530940029, "count": 67434, "self": 981.6081273748732, "children": { "SubprocessEnvManager._take_step": { "total": 243.2612496371121, "count": 67434, "self": 4.573232782031937, "children": { "TorchPolicy.evaluate": { "total": 238.68801685508015, "count": 65919, "self": 238.68801685508015 } } }, "workers": { "total": 0.8190760820175456, "count": 67433, "self": 0.0, "children": { "worker_root": { "total": 1941.6785343919369, "count": 67433, "is_parallel": true, "self": 1043.4150026517777, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002136932999746932, "count": 1, "is_parallel": true, "self": 0.001040155999817216, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010967769999297161, "count": 8, "is_parallel": true, "self": 0.0010967769999297161 } } }, "UnityEnvironment.step": { "total": 0.02504521399987425, "count": 1, "is_parallel": true, "self": 0.0001749469997776032, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001465629998165241, "count": 1, "is_parallel": true, "self": 0.0001465629998165241 }, "communicator.exchange": { "total": 0.024186590000226715, "count": 1, "is_parallel": true, "self": 0.024186590000226715 }, "steps_from_proto": { "total": 0.0005371140000534069, "count": 1, "is_parallel": true, "self": 0.00012083900037396234, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004162749996794446, "count": 8, "is_parallel": true, "self": 0.0004162749996794446 } } } } } } }, "UnityEnvironment.step": { "total": 898.2635317401591, "count": 67432, "is_parallel": true, "self": 13.010326372182135, "children": { "UnityEnvironment._generate_step_input": { "total": 9.26200430490826, "count": 67432, "is_parallel": true, "self": 9.26200430490826 }, "communicator.exchange": { "total": 839.308260034084, "count": 67432, "is_parallel": true, "self": 839.308260034084 }, "steps_from_proto": { "total": 36.682941028984715, "count": 67432, "is_parallel": true, "self": 8.480433917803566, "children": { "_process_rank_one_or_two_observation": { "total": 28.20250711118115, "count": 539456, "is_parallel": true, "self": 28.20250711118115 } } } } } } } } } } }, "trainer_advance": { "total": 714.7001866529113, "count": 67433, "self": 2.2681803059026606, "children": { "process_trajectory": { "total": 111.5056090560156, "count": 67433, "self": 111.30473352201534, "children": { "RLTrainer._checkpoint": { "total": 0.2008755340002608, "count": 2, "self": 0.2008755340002608 } } }, "_update_policy": { "total": 600.926397290993, "count": 475, "self": 272.4638784309418, "children": { "TorchPPOOptimizer.update": { "total": 328.4625188600512, "count": 24006, "self": 328.4625188600512 } } } } } } }, "trainer_threads": { "total": 1.2430000424501486e-06, "count": 1, "self": 1.2430000424501486e-06 }, "TrainerController._save_models": { "total": 0.11028296499989665, "count": 1, "self": 0.0008767660001467448, "children": { "RLTrainer._checkpoint": { "total": 0.1094061989997499, "count": 1, "self": 0.1094061989997499 } } } } } } }