{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3910399079322815, "min": 0.3910399079322815, "max": 1.4689998626708984, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11699.9140625, "min": 11699.9140625, "max": 44563.578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989951.0, "min": 29952.0, "max": 989951.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989951.0, "min": 29952.0, "max": 989951.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.47697100043296814, "min": -0.10495811700820923, "max": 0.5399703979492188, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.73611450195312, "min": -25.399864196777344, "max": 150.1117706298828, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.05224237218499184, "min": 0.004186338745057583, "max": 0.3076922595500946, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 14.209925651550293, "min": 1.1135661602020264, "max": 72.92306518554688, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06809086802200166, "min": 0.0662989716875353, "max": 0.07462315467556876, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9532721523080232, "min": 0.48647728766500015, "max": 1.0714387398620602, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013916763951350556, "min": 0.000607906276850999, "max": 0.014474219039368023, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1948346953189078, "min": 0.004863250214807992, "max": 0.20263906655115232, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.556690338278574e-06, "min": 7.556690338278574e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010579366473590004, "min": 0.00010579366473590004, "max": 0.003508478930507099, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251886428571431, "min": 0.10251886428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352641000000004, "min": 1.3691136000000002, "max": 2.5694929, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002616345421428572, "min": 0.0002616345421428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003662883590000001, "min": 0.003662883590000001, "max": 0.11697234071000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012807240709662437, "min": 0.012807240709662437, "max": 0.3628281056880951, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17930136620998383, "min": 0.17930136620998383, "max": 2.539796829223633, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 378.11392405063293, "min": 333.7469879518072, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29871.0, "min": 15984.0, "max": 33651.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4699316219061236, "min": -1.0000000521540642, "max": 1.61613900623307, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 116.12459813058376, "min": -32.000001668930054, "max": 132.52339851111174, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4699316219061236, "min": -1.0000000521540642, "max": 1.61613900623307, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 116.12459813058376, "min": -32.000001668930054, "max": 132.52339851111174, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.050428466184125165, "min": 0.047367781655161596, "max": 7.6537875179201365, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.983848828545888, "min": 3.884158095723251, "max": 122.46060028672218, "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": "1728854938", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728857154" }, "total": 2215.929803569, "count": 1, "self": 0.4267251210003451, "children": { "run_training.setup": { "total": 0.050548281999908795, "count": 1, "self": 0.050548281999908795 }, "TrainerController.start_learning": { "total": 2215.4525301659996, "count": 1, "self": 1.3782752199590504, "children": { "TrainerController._reset_env": { "total": 1.8070162740000342, "count": 1, "self": 1.8070162740000342 }, "TrainerController.advance": { "total": 2212.17558907704, "count": 63724, "self": 1.3977412758899845, "children": { "env_step": { "total": 1535.2886008220921, "count": 63724, "self": 1387.5131935621203, "children": { "SubprocessEnvManager._take_step": { "total": 146.99574192592718, "count": 63724, "self": 4.517643887924351, "children": { "TorchPolicy.evaluate": { "total": 142.47809803800283, "count": 62570, "self": 142.47809803800283 } } }, "workers": { "total": 0.7796653340446937, "count": 63724, "self": 0.0, "children": { "worker_root": { "total": 2210.9705247750476, "count": 63724, "is_parallel": true, "self": 938.1472836262024, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002303956000105245, "count": 1, "is_parallel": true, "self": 0.0007092549999470066, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015947010001582385, "count": 8, "is_parallel": true, "self": 0.0015947010001582385 } } }, "UnityEnvironment.step": { "total": 0.047291139000208204, "count": 1, "is_parallel": true, "self": 0.0006011950003994571, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004538329999377311, "count": 1, "is_parallel": true, "self": 0.0004538329999377311 }, "communicator.exchange": { "total": 0.044600916000035795, "count": 1, "is_parallel": true, "self": 0.044600916000035795 }, "steps_from_proto": { "total": 0.001635194999835221, "count": 1, "is_parallel": true, "self": 0.0003509000002850371, "children": { "_process_rank_one_or_two_observation": { "total": 0.001284294999550184, "count": 8, "is_parallel": true, "self": 0.001284294999550184 } } } } } } }, "UnityEnvironment.step": { "total": 1272.8232411488452, "count": 63723, "is_parallel": true, "self": 32.588595302787326, "children": { "UnityEnvironment._generate_step_input": { "total": 22.933508745989002, "count": 63723, "is_parallel": true, "self": 22.933508745989002 }, "communicator.exchange": { "total": 1122.9947438770305, "count": 63723, "is_parallel": true, "self": 1122.9947438770305 }, "steps_from_proto": { "total": 94.30639322303841, "count": 63723, "is_parallel": true, "self": 18.646696834241993, "children": { "_process_rank_one_or_two_observation": { "total": 75.65969638879642, "count": 509784, "is_parallel": true, "self": 75.65969638879642 } } } } } } } } } } }, "trainer_advance": { "total": 675.489246979058, "count": 63724, "self": 2.481567199042729, "children": { "process_trajectory": { "total": 131.10887412401325, "count": 63724, "self": 130.90869047601336, "children": { "RLTrainer._checkpoint": { "total": 0.20018364799989286, "count": 2, "self": 0.20018364799989286 } } }, "_update_policy": { "total": 541.898805656002, "count": 444, "self": 305.81680782305966, "children": { "TorchPPOOptimizer.update": { "total": 236.0819978329423, "count": 22785, "self": 236.0819978329423 } } } } } } }, "trainer_threads": { "total": 1.0439998732181266e-06, "count": 1, "self": 1.0439998732181266e-06 }, "TrainerController._save_models": { "total": 0.09164855100061686, "count": 1, "self": 0.0013057100004516542, "children": { "RLTrainer._checkpoint": { "total": 0.09034284100016521, "count": 1, "self": 0.09034284100016521 } } } } } } }