{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6958231329917908, "min": 0.695159375667572, "max": 1.5101449489593506, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 20986.025390625, "min": 20654.576171875, "max": 45811.7578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989948.0, "min": 29952.0, "max": 989948.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3247838020324707, "min": -0.10884139686822891, "max": 0.327345073223114, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 83.79421997070312, "min": -26.339618682861328, "max": 85.43706512451172, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.26233866810798645, "min": -0.5807990431785583, "max": 0.2811756134033203, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -67.68338012695312, "min": -151.5885467529297, "max": 67.48214721679688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07073254587133404, "min": 0.0640710620749517, "max": 0.07454552525742153, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9902556421986766, "min": 0.48525310727605736, "max": 1.0583808723530121, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018322317129776635, "min": 0.0002405607651615788, "max": 0.05514608729503206, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2565124398168729, "min": 0.002646168416777367, "max": 0.7720452221304488, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.655326019685712e-06, "min": 7.655326019685712e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010717456427559997, "min": 0.00010717456427559997, "max": 0.0032235613254796005, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10255174285714286, "min": 0.10255174285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4357244, "min": 1.3691136000000002, "max": 2.3586104, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026491911142857136, "min": 0.00026491911142857136, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003708867559999999, "min": 0.003708867559999999, "max": 0.10746458796000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010823513381183147, "min": 0.010823513381183147, "max": 0.4958982467651367, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1515291929244995, "min": 0.1515291929244995, "max": 3.471287727355957, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 529.0535714285714, "min": 508.6666666666667, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29627.0, "min": 15984.0, "max": 32756.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.191775405616091, "min": -1.0000000521540642, "max": 1.3104576643269796, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 67.93119812011719, "min": -32.000001668930054, "max": 73.65879831463099, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.191775405616091, "min": -1.0000000521540642, "max": 1.3104576643269796, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 67.93119812011719, "min": -32.000001668930054, "max": 73.65879831463099, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05933543884097353, "min": 0.05912336801508597, "max": 10.230432529002428, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3821200139354914, "min": 3.254593529563863, "max": 163.68692046403885, "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": "1749120252", "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 --torch-device cuda:0 --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749122554" }, "total": 2301.7872748990003, "count": 1, "self": 0.4892918160003319, "children": { "run_training.setup": { "total": 0.020193182000184606, "count": 1, "self": 0.020193182000184606 }, "TrainerController.start_learning": { "total": 2301.277789901, "count": 1, "self": 1.543196157024795, "children": { "TrainerController._reset_env": { "total": 2.2374321480001527, "count": 1, "self": 2.2374321480001527 }, "TrainerController.advance": { "total": 2297.4113840859754, "count": 63354, "self": 1.6244186958574574, "children": { "env_step": { "total": 1600.6495524949933, "count": 63354, "self": 1432.1697028759872, "children": { "SubprocessEnvManager._take_step": { "total": 167.55862792293237, "count": 63354, "self": 5.109585797045838, "children": { "TorchPolicy.evaluate": { "total": 162.44904212588654, "count": 62567, "self": 162.44904212588654 } } }, "workers": { "total": 0.9212216960736441, "count": 63354, "self": 0.0, "children": { "worker_root": { "total": 2295.6027523599296, "count": 63354, "is_parallel": true, "self": 988.0951814238852, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019670419997055433, "count": 1, "is_parallel": true, "self": 0.0006958539997867774, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012711879999187659, "count": 8, "is_parallel": true, "self": 0.0012711879999187659 } } }, "UnityEnvironment.step": { "total": 0.050322376000167424, "count": 1, "is_parallel": true, "self": 0.0005681970001205627, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005280989998937002, "count": 1, "is_parallel": true, "self": 0.0005280989998937002 }, "communicator.exchange": { "total": 0.047556134999922506, "count": 1, "is_parallel": true, "self": 0.047556134999922506 }, "steps_from_proto": { "total": 0.0016699450002306548, "count": 1, "is_parallel": true, "self": 0.00034528900096120196, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013246559992694529, "count": 8, "is_parallel": true, "self": 0.0013246559992694529 } } } } } } }, "UnityEnvironment.step": { "total": 1307.5075709360444, "count": 63353, "is_parallel": true, "self": 33.53295013090883, "children": { "UnityEnvironment._generate_step_input": { "total": 24.44629725903269, "count": 63353, "is_parallel": true, "self": 24.44629725903269 }, "communicator.exchange": { "total": 1145.8638572530767, "count": 63353, "is_parallel": true, "self": 1145.8638572530767 }, "steps_from_proto": { "total": 103.66446629302618, "count": 63353, "is_parallel": true, "self": 21.507417407189223, "children": { "_process_rank_one_or_two_observation": { "total": 82.15704888583696, "count": 506824, "is_parallel": true, "self": 82.15704888583696 } } } } } } } } } } }, "trainer_advance": { "total": 695.1374128951247, "count": 63354, "self": 2.87197399315437, "children": { "process_trajectory": { "total": 136.07378579897158, "count": 63354, "self": 135.80361485897174, "children": { "RLTrainer._checkpoint": { "total": 0.27017093999984354, "count": 2, "self": 0.27017093999984354 } } }, "_update_policy": { "total": 556.1916531029988, "count": 437, "self": 308.30970096200554, "children": { "TorchPPOOptimizer.update": { "total": 247.88195214099323, "count": 22869, "self": 247.88195214099323 } } } } } } }, "trainer_threads": { "total": 1.2689997674897313e-06, "count": 1, "self": 1.2689997674897313e-06 }, "TrainerController._save_models": { "total": 0.08577624099962122, "count": 1, "self": 0.0018109589991581743, "children": { "RLTrainer._checkpoint": { "total": 0.08396528200046305, "count": 1, "self": 0.08396528200046305 } } } } } } }