{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.30509909987449646, "min": 0.28990447521209717, "max": 1.441232681274414, "count": 36 }, "Pyramids.Policy.Entropy.sum": { "value": 9143.2099609375, "min": 8803.8193359375, "max": 43721.234375, "count": 36 }, "Pyramids.Step.mean": { "value": 1079984.0, "min": 29952.0, "max": 1079984.0, "count": 36 }, "Pyramids.Step.sum": { "value": 1079984.0, "min": 29952.0, "max": 1079984.0, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8093224167823792, "min": -0.09491204470396042, "max": 0.8093224167823792, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 241.98741149902344, "min": -22.873802185058594, "max": 241.98741149902344, "count": 36 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01239005383104086, "min": 0.00574734341353178, "max": 0.35108333826065063, "count": 36 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.7046260833740234, "min": 1.5517827272415161, "max": 84.611083984375, "count": 36 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0697943407015243, "min": 0.0632451926855948, "max": 0.07381784548914308, "count": 36 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9771207698213401, "min": 0.49524930614890095, "max": 1.1072676823371461, "count": 36 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014308287641532453, "min": 0.0003681616052286885, "max": 0.01701101736873287, "count": 36 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20031602698145434, "min": 0.004049777657515573, "max": 0.2384952600938656, "count": 36 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019349389264490476, "min": 0.00019349389264490476, "max": 0.00029838354339596195, "count": 36 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0027089144970286667, "min": 0.0020886848037717336, "max": 0.004072603942465399, "count": 36 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1644979523809524, "min": 0.1644979523809524, "max": 0.19946118095238097, "count": 36 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3029713333333337, "min": 1.3962282666666668, "max": 2.8575345999999997, "count": 36 }, "Pyramids.Policy.Beta.mean": { "value": 0.006453345442857143, "min": 0.006453345442857143, "max": 0.009946171977142856, "count": 36 }, "Pyramids.Policy.Beta.sum": { "value": 0.0903468362, "min": 0.06962320384, "max": 0.13576770653999998, "count": 36 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.02427729032933712, "min": 0.023986907675862312, "max": 0.5884901285171509, "count": 36 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.3398820757865906, "min": 0.3118298053741455, "max": 4.119431018829346, "count": 36 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 234.072, "min": 234.072, "max": 999.0, "count": 36 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29259.0, "min": 15984.0, "max": 33718.0, "count": 36 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7659279786348343, "min": -1.0000000521540642, "max": 1.7659279786348343, "count": 36 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 220.7409973293543, "min": -29.445601865649223, "max": 220.7409973293543, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7659279786348343, "min": -1.0000000521540642, "max": 1.7659279786348343, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 220.7409973293543, "min": -29.445601865649223, "max": 220.7409973293543, "count": 36 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05790819965582341, "min": 0.05790819965582341, "max": 11.497447066009045, "count": 36 }, "Pyramids.Policy.RndReward.sum": { "value": 7.238524956977926, "min": 7.1070929108100245, "max": 183.95915305614471, "count": 36 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1793482208", "python_version": "3.10.22 (main, Oct 9 2026, 15:21:30) [Clang 22.1.3 ]", "command_line_arguments": "/content/ml-venv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --torch-device=cpu", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1793486259" }, "total": 4051.298203068, "count": 1, "self": 1.576768235000145, "children": { "run_training.setup": { "total": 0.03316825100000642, "count": 1, "self": 0.03316825100000642 }, "TrainerController.start_learning": { "total": 4049.688266582, "count": 1, "self": 2.6555920710884493, "children": { "TrainerController._reset_env": { "total": 2.7451349199996002, "count": 1, "self": 2.7451349199996002 }, "TrainerController.advance": { "total": 4044.1576429089114, "count": 70032, "self": 2.7745865579067868, "children": { "env_step": { "total": 2876.1458819029494, "count": 70032, "self": 2697.800244721085, "children": { "SubprocessEnvManager._take_step": { "total": 176.77132676299016, "count": 70032, "self": 7.546090799994545, "children": { "TorchPolicy.evaluate": { "total": 169.2252359629956, "count": 68014, "self": 169.2252359629956 } } }, "workers": { "total": 1.57431041887412, "count": 70031, "self": 0.0, "children": { "worker_root": { "total": 4040.5499199341293, "count": 70031, "is_parallel": true, "self": 1541.5908455981926, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0031838969998716493, "count": 1, "is_parallel": true, "self": 0.0010891960005210422, "children": { "_process_rank_one_or_two_observation": { "total": 0.002094700999350607, "count": 8, "is_parallel": true, "self": 0.002094700999350607 } } }, "UnityEnvironment.step": { "total": 0.06079097100018771, "count": 1, "is_parallel": true, "self": 0.000682471999880363, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005222800000410643, "count": 1, "is_parallel": true, "self": 0.0005222800000410643 }, "communicator.exchange": { "total": 0.05728503599993928, "count": 1, "is_parallel": true, "self": 0.05728503599993928 }, "steps_from_proto": { "total": 0.0023011830003270006, "count": 1, "is_parallel": true, "self": 0.0004560020001918019, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018451810001351987, "count": 8, "is_parallel": true, "self": 0.0018451810001351987 } } } } } } }, "UnityEnvironment.step": { "total": 2498.9590743359367, "count": 70030, "is_parallel": true, "self": 49.72803420794662, "children": { "UnityEnvironment._generate_step_input": { "total": 33.25431771810145, "count": 70030, "is_parallel": true, "self": 33.25431771810145 }, "communicator.exchange": { "total": 2253.959363644846, "count": 70030, "is_parallel": true, "self": 2253.959363644846 }, "steps_from_proto": { "total": 162.0173587650429, "count": 70030, "is_parallel": true, "self": 33.3103062060527, "children": { "_process_rank_one_or_two_observation": { "total": 128.7070525589902, "count": 560240, "is_parallel": true, "self": 128.7070525589902 } } } } } } } } } } }, "trainer_advance": { "total": 1165.2371744480552, "count": 70031, "self": 5.091981570049484, "children": { "process_trajectory": { "total": 168.39986665300012, "count": 70031, "self": 168.20992827800046, "children": { "RLTrainer._checkpoint": { "total": 0.18993837499965593, "count": 2, "self": 0.18993837499965593 } } }, "_update_policy": { "total": 991.7453262250056, "count": 496, "self": 399.614872157033, "children": { "TorchPPOOptimizer.update": { "total": 592.1304540679726, "count": 24795, "self": 592.1304540679726 } } } } } } }, "trainer_threads": { "total": 2.153999957954511e-06, "count": 1, "self": 2.153999957954511e-06 }, "TrainerController._save_models": { "total": 0.1298945280004773, "count": 1, "self": 0.0039637410000068485, "children": { "RLTrainer._checkpoint": { "total": 0.12593078700047045, "count": 1, "self": 0.12593078700047045 } } } } } } }