{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.837311327457428, "min": 0.7887104749679565, "max": 1.469686508178711, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 25065.751953125, "min": 23623.45703125, "max": 44584.41015625, "count": 33 }, "Pyramids.Step.mean": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989982.0, "min": 29952.0, "max": 989982.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.06642565131187439, "min": -0.16104307770729065, "max": 0.14297114312648773, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 16.27428436279297, "min": -38.16720962524414, "max": 36.17169952392578, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.025431759655475616, "min": -0.06733652204275131, "max": 0.30287840962409973, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.230781078338623, "min": -16.96880340576172, "max": 72.99369812011719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06552543547955565, "min": 0.06552543547955565, "max": 0.07366455763008571, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9828815321933349, "min": 0.5156519034106, "max": 1.060121506780121, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.006884446493345689, "min": 0.0006709692115277738, "max": 0.010788520641220939, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.10326669740018533, "min": 0.00890061046903283, "max": 0.15103928897709315, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4177975274333314e-06, "min": 7.4177975274333314e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011126696291149997, "min": 0.00011126696291149997, "max": 0.0032261200246267003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247256666666667, "min": 0.10247256666666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5370885, "min": 1.3886848, "max": 2.3598060000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025700941, "min": 0.00025700941, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038551411499999997, "min": 0.0038551411499999997, "max": 0.10754979267000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014785146340727806, "min": 0.014499468728899956, "max": 0.43704846501350403, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.22177720069885254, "min": 0.20299255847930908, "max": 3.0593392848968506, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 817.7428571428571, "min": 664.9111111111112, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28621.0, "min": 15984.0, "max": 33374.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.09615995628493172, "min": -1.0000000521540642, "max": 0.7126532935433918, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 3.3655984699726105, "min": -29.720401614904404, "max": 32.06939820945263, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.09615995628493172, "min": -1.0000000521540642, "max": 0.7126532935433918, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 3.3655984699726105, "min": -29.720401614904404, "max": 32.06939820945263, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.12650357860007455, "min": 0.09950008938580544, "max": 8.075279124081135, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.42762525100261, "min": 4.42762525100261, "max": 129.20446598529816, "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": "1718814642", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718816674" }, "total": 2031.802959925, "count": 1, "self": 0.7300454520002404, "children": { "run_training.setup": { "total": 0.05360960799998793, "count": 1, "self": 0.05360960799998793 }, "TrainerController.start_learning": { "total": 2031.0193048649999, "count": 1, "self": 1.2550726110050618, "children": { "TrainerController._reset_env": { "total": 2.635279113000024, "count": 1, "self": 2.635279113000024 }, "TrainerController.advance": { "total": 2026.9848146969948, "count": 63097, "self": 1.3615411590353688, "children": { "env_step": { "total": 1404.3245475619829, "count": 63097, "self": 1277.7633800289802, "children": { "SubprocessEnvManager._take_step": { "total": 125.80361632400809, "count": 63097, "self": 4.5362445650430345, "children": { "TorchPolicy.evaluate": { "total": 121.26737175896506, "count": 62574, "self": 121.26737175896506 } } }, "workers": { "total": 0.7575512089945278, "count": 63097, "self": 0.0, "children": { "worker_root": { "total": 2026.2169061950049, "count": 63097, "is_parallel": true, "self": 863.3552926260238, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020610029998806567, "count": 1, "is_parallel": true, "self": 0.0005763550000210671, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014846479998595896, "count": 8, "is_parallel": true, "self": 0.0014846479998595896 } } }, "UnityEnvironment.step": { "total": 0.06994037999993452, "count": 1, "is_parallel": true, "self": 0.0006256759997995687, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004221180001877656, "count": 1, "is_parallel": true, "self": 0.0004221180001877656 }, "communicator.exchange": { "total": 0.06734133499980999, "count": 1, "is_parallel": true, "self": 0.06734133499980999 }, "steps_from_proto": { "total": 0.0015512510001371993, "count": 1, "is_parallel": true, "self": 0.0003161659999477706, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012350850001894287, "count": 8, "is_parallel": true, "self": 0.0012350850001894287 } } } } } } }, "UnityEnvironment.step": { "total": 1162.861613568981, "count": 63096, "is_parallel": true, "self": 32.84048656204368, "children": { "UnityEnvironment._generate_step_input": { "total": 22.549250934976726, "count": 63096, "is_parallel": true, "self": 22.549250934976726 }, "communicator.exchange": { "total": 1012.9280660169338, "count": 63096, "is_parallel": true, "self": 1012.9280660169338 }, "steps_from_proto": { "total": 94.54381005502682, "count": 63096, "is_parallel": true, "self": 18.501942053943367, "children": { "_process_rank_one_or_two_observation": { "total": 76.04186800108346, "count": 504768, "is_parallel": true, "self": 76.04186800108346 } } } } } } } } } } }, "trainer_advance": { "total": 621.2987259759766, "count": 63097, "self": 2.424844886013261, "children": { "process_trajectory": { "total": 123.41343956696073, "count": 63097, "self": 123.17311942696142, "children": { "RLTrainer._checkpoint": { "total": 0.24032013999931223, "count": 2, "self": 0.24032013999931223 } } }, "_update_policy": { "total": 495.4604415230026, "count": 441, "self": 293.34131712902195, "children": { "TorchPPOOptimizer.update": { "total": 202.11912439398066, "count": 22806, "self": 202.11912439398066 } } } } } } }, "trainer_threads": { "total": 1.238000095327152e-06, "count": 1, "self": 1.238000095327152e-06 }, "TrainerController._save_models": { "total": 0.14413720599986846, "count": 1, "self": 0.0018808379995789437, "children": { "RLTrainer._checkpoint": { "total": 0.1422563680002895, "count": 1, "self": 0.1422563680002895 } } } } } } }