{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.28874826431274414, "min": 0.28799375891685486, "max": 1.4167274236679077, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8704.02734375, "min": 8612.1650390625, "max": 42977.84375, "count": 33 }, "Pyramids.Step.mean": { "value": 989934.0, "min": 29952.0, "max": 989934.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989934.0, "min": 29952.0, "max": 989934.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5555307865142822, "min": -0.09557277709245682, "max": 0.6632574200630188, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 151.659912109375, "min": -22.93746566772461, "max": 191.681396484375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00242367060855031, "min": -0.1786683201789856, "max": 0.3713178038597107, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.6616621017456055, "min": -46.989768981933594, "max": 88.0023193359375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07172153633984549, "min": 0.06530367043322056, "max": 0.07490418907920164, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0041015087578369, "min": 0.4977167543397156, "max": 1.079499623665755, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014853488293565097, "min": 0.00026929999669677445, "max": 0.018629020147186346, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20794883610991136, "min": 0.0032315999603612935, "max": 0.26080628206060885, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.384468967114283e-06, "min": 7.384468967114283e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010338256553959997, "min": 0.00010338256553959997, "max": 0.0036345421884860004, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246145714285713, "min": 0.10246145714285713, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344603999999999, "min": 1.3886848, "max": 2.662620300000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025589956857142857, "min": 0.00025589956857142857, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00358259396, "min": 0.00358259396, "max": 0.12117024859999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010907362215220928, "min": 0.010907362215220928, "max": 0.46725723147392273, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15270307660102844, "min": 0.15270307660102844, "max": 3.2708005905151367, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 326.01162790697674, "min": 286.3592233009709, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28037.0, "min": 15984.0, "max": 32198.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6068045695622761, "min": -1.0000000521540642, "max": 1.694215516731577, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 139.79199755191803, "min": -29.50300160050392, "max": 174.50419822335243, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6068045695622761, "min": -1.0000000521540642, "max": 1.694215516731577, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 139.79199755191803, "min": -29.50300160050392, "max": 174.50419822335243, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.036753509975615196, "min": 0.034706200959016255, "max": 8.72353034093976, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.197555367878522, "min": 3.197555367878522, "max": 139.57648545503616, "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": "1785244211", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1785246685" }, "total": 2474.704850659, "count": 1, "self": 0.48188655100057076, "children": { "run_training.setup": { "total": 0.02407745599998634, "count": 1, "self": 0.02407745599998634 }, "TrainerController.start_learning": { "total": 2474.1988866519996, "count": 1, "self": 1.4009894140590404, "children": { "TrainerController._reset_env": { "total": 2.1001859259999947, "count": 1, "self": 2.1001859259999947 }, "TrainerController.advance": { "total": 2470.6249303529407, "count": 64223, "self": 1.424324903933666, "children": { "env_step": { "total": 1840.6942319810125, "count": 64223, "self": 1688.9804382189952, "children": { "SubprocessEnvManager._take_step": { "total": 150.87593891800225, "count": 64223, "self": 4.6893423479334615, "children": { "TorchPolicy.evaluate": { "total": 146.1865965700688, "count": 62571, "self": 146.1865965700688 } } }, "workers": { "total": 0.8378548440150553, "count": 64223, "self": 0.0, "children": { "worker_root": { "total": 2468.3344161458667, "count": 64223, "is_parallel": true, "self": 898.932100925857, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017611549999401177, "count": 1, "is_parallel": true, "self": 0.000586303000090993, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011748519998491247, "count": 8, "is_parallel": true, "self": 0.0011748519998491247 } } }, "UnityEnvironment.step": { "total": 0.05134154400002444, "count": 1, "is_parallel": true, "self": 0.0005398519999744167, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004943330000060087, "count": 1, "is_parallel": true, "self": 0.0004943330000060087 }, "communicator.exchange": { "total": 0.04867942300006689, "count": 1, "is_parallel": true, "self": 0.04867942300006689 }, "steps_from_proto": { "total": 0.001627935999977126, "count": 1, "is_parallel": true, "self": 0.0003827469997759181, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012451890002012078, "count": 8, "is_parallel": true, "self": 0.0012451890002012078 } } } } } } }, "UnityEnvironment.step": { "total": 1569.4023152200098, "count": 64222, "is_parallel": true, "self": 33.826823968032386, "children": { "UnityEnvironment._generate_step_input": { "total": 23.486220446953894, "count": 64222, "is_parallel": true, "self": 23.486220446953894 }, "communicator.exchange": { "total": 1402.7791468410726, "count": 64222, "is_parallel": true, "self": 1402.7791468410726 }, "steps_from_proto": { "total": 109.3101239639509, "count": 64222, "is_parallel": true, "self": 22.631807794143924, "children": { "_process_rank_one_or_two_observation": { "total": 86.67831616980698, "count": 513776, "is_parallel": true, "self": 86.67831616980698 } } } } } } } } } } }, "trainer_advance": { "total": 628.5063734679945, "count": 64223, "self": 2.7720307919912557, "children": { "process_trajectory": { "total": 113.23971866400188, "count": 64223, "self": 113.06028520100153, "children": { "RLTrainer._checkpoint": { "total": 0.17943346300035046, "count": 2, "self": 0.17943346300035046 } } }, "_update_policy": { "total": 512.4946240120014, "count": 456, "self": 272.69853448904064, "children": { "TorchPPOOptimizer.update": { "total": 239.79608952296076, "count": 22791, "self": 239.79608952296076 } } } } } } }, "trainer_threads": { "total": 8.580000212532468e-07, "count": 1, "self": 8.580000212532468e-07 }, "TrainerController._save_models": { "total": 0.07278010099980747, "count": 1, "self": 0.0010728240004027612, "children": { "RLTrainer._checkpoint": { "total": 0.07170727699940471, "count": 1, "self": 0.07170727699940471 } } } } } } }