{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8482744097709656, "min": 0.8238581418991089, "max": 1.3770806789398193, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 25231.07421875, "min": 24465.291015625, "max": 41775.12109375, "count": 16 }, "Pyramids.Step.mean": { "value": 479953.0, "min": 29952.0, "max": 479953.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479953.0, "min": 29952.0, "max": 479953.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1001254990696907, "min": -0.09756134450435638, "max": 0.26537954807281494, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 24.931249618530273, "min": -23.512283325195312, "max": 62.894954681396484, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025898238644003868, "min": 0.023176442831754684, "max": 0.47287121415138245, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.4486613273620605, "min": 5.655052185058594, "max": 112.07048034667969, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06744945801295171, "min": 0.06413263848596983, "max": 0.07580344352214742, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.944292412181324, "min": 0.530624104655032, "max": 1.0091975809579405, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.008235233433030694, "min": 0.00034471488094860544, "max": 0.011257351826661132, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11529326806242973, "min": 0.0041365785713832655, "max": 0.11529326806242973, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.0728635947628568e-05, "min": 2.0728635947628568e-05, "max": 0.00029030126037577137, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00029020090326679996, "min": 0.00029020090326679996, "max": 0.0030851756716082, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10690951428571428, "min": 0.10690951428571428, "max": 0.19676708571428575, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4967332, "min": 1.3773696000000002, "max": 2.3389688, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0007002604771428573, "min": 0.0007002604771428573, "max": 0.00967703186285714, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.009803646680000002, "min": 0.009803646680000002, "max": 0.10286634082000001, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.024802012369036674, "min": 0.024802012369036674, "max": 0.5258089900016785, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.34722816944122314, "min": 0.34722816944122314, "max": 3.6806631088256836, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 777.725, "min": 777.725, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31109.0, "min": 15984.0, "max": 32685.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.47200495805591347, "min": -1.0000000521540642, "max": 0.47200495805591347, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 18.880198322236538, "min": -31.998801693320274, "max": 18.880198322236538, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.47200495805591347, "min": -1.0000000521540642, "max": 0.47200495805591347, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 18.880198322236538, "min": -31.998801693320274, "max": 18.880198322236538, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.20378975550411269, "min": 0.20378975550411269, "max": 11.0823162663728, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 8.151590220164508, "min": 8.151590220164508, "max": 177.3170602619648, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1728710997", "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": "1728712039" }, "total": 1042.6718296469999, "count": 1, "self": 0.494355411000015, "children": { "run_training.setup": { "total": 0.056343589999983124, "count": 1, "self": 0.056343589999983124 }, "TrainerController.start_learning": { "total": 1042.121130646, "count": 1, "self": 0.6655041160024666, "children": { "TrainerController._reset_env": { "total": 2.556922285999974, "count": 1, "self": 2.556922285999974 }, "TrainerController.advance": { "total": 1038.8155495239973, "count": 31575, "self": 0.6855038910177882, "children": { "env_step": { "total": 692.0674005139838, "count": 31575, "self": 615.8416372670064, "children": { "SubprocessEnvManager._take_step": { "total": 75.82687134398492, "count": 31575, "self": 2.2725660590109555, "children": { "TorchPolicy.evaluate": { "total": 73.55430528497396, "count": 31295, "self": 73.55430528497396 } } }, "workers": { "total": 0.39889190299248867, "count": 31575, "self": 0.0, "children": { "worker_root": { "total": 1039.6019978100187, "count": 31575, "is_parallel": true, "self": 482.5742403670206, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00209915400000682, "count": 1, "is_parallel": true, "self": 0.0006228100000953418, "children": { "_process_rank_one_or_two_observation": { "total": 0.001476343999911478, "count": 8, "is_parallel": true, "self": 0.001476343999911478 } } }, "UnityEnvironment.step": { "total": 0.057373281000025145, "count": 1, "is_parallel": true, "self": 0.0006079620000605246, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004718740000271282, "count": 1, "is_parallel": true, "self": 0.0004718740000271282 }, "communicator.exchange": { "total": 0.05478363999998237, "count": 1, "is_parallel": true, "self": 0.05478363999998237 }, "steps_from_proto": { "total": 0.0015098049999551222, "count": 1, "is_parallel": true, "self": 0.0003008470000054331, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012089579999496891, "count": 8, "is_parallel": true, "self": 0.0012089579999496891 } } } } } } }, "UnityEnvironment.step": { "total": 557.0277574429981, "count": 31574, "is_parallel": true, "self": 16.579979727009686, "children": { "UnityEnvironment._generate_step_input": { "total": 11.314982642003486, "count": 31574, "is_parallel": true, "self": 11.314982642003486 }, "communicator.exchange": { "total": 482.1058485129947, "count": 31574, "is_parallel": true, "self": 482.1058485129947 }, "steps_from_proto": { "total": 47.02694656099021, "count": 31574, "is_parallel": true, "self": 9.431337442942493, "children": { "_process_rank_one_or_two_observation": { "total": 37.59560911804772, "count": 252592, "is_parallel": true, "self": 37.59560911804772 } } } } } } } } } } }, "trainer_advance": { "total": 346.0626451189957, "count": 31575, "self": 1.2273609859848307, "children": { "process_trajectory": { "total": 65.45234130701198, "count": 31575, "self": 65.26030450401191, "children": { "RLTrainer._checkpoint": { "total": 0.19203680300006454, "count": 1, "self": 0.19203680300006454 } } }, "_update_policy": { "total": 279.3829428259989, "count": 218, "self": 157.43463760499918, "children": { "TorchPPOOptimizer.update": { "total": 121.94830522099971, "count": 11418, "self": 121.94830522099971 } } } } } } }, "trainer_threads": { "total": 1.0000001111620804e-06, "count": 1, "self": 1.0000001111620804e-06 }, "TrainerController._save_models": { "total": 0.08315372000015486, "count": 1, "self": 0.001286994000111008, "children": { "RLTrainer._checkpoint": { "total": 0.08186672600004385, "count": 1, "self": 0.08186672600004385 } } } } } } }