{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4876851439476013, "min": 0.4876851439476013, "max": 1.50128972530365, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14833.431640625, "min": 14799.7392578125, "max": 45543.125, "count": 33 }, "Pyramids.Step.mean": { "value": 989879.0, "min": 29895.0, "max": 989879.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989879.0, "min": 29895.0, "max": 989879.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3546045422554016, "min": -0.09798877686262131, "max": 0.40142837166786194, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 93.6156005859375, "min": -23.51730728149414, "max": 104.7728042602539, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0006557323504239321, "min": -0.6742866039276123, "max": 0.36897242069244385, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.17311334609985352, "min": -176.6630859375, "max": 87.44646453857422, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06944293210842009, "min": 0.06384807716805133, "max": 0.07255164059849102, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9722010495178812, "min": 0.5667429176542654, "max": 1.0238074502318768, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013588541115982494, "min": 0.0006994268578100945, "max": 0.052272423012851704, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1902395756237549, "min": 0.006994268578100945, "max": 0.7840863451927755, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.844561670892852e-06, "min": 7.844561670892852e-06, "max": 0.0002952118890960375, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010982386339249993, "min": 0.00010982386339249993, "max": 0.0033822335725888996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10261482142857141, "min": 0.10261482142857141, "max": 0.19840396249999998, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4366074999999998, "min": 1.4366074999999998, "max": 2.5274111, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002712206607142856, "min": 0.0002712206607142856, "max": 0.00984055585375, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037970892499999986, "min": 0.0037970892499999986, "max": 0.11276836889000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011304235085844994, "min": 0.011304235085844994, "max": 0.548721432685852, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1582592874765396, "min": 0.1582592874765396, "max": 4.389771461486816, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 452.7692307692308, "min": 452.4923076923077, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29430.0, "min": 16822.0, "max": 33900.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3317784430888984, "min": -1.0000000521540642, "max": 1.3320461183786392, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 86.56559880077839, "min": -32.000001668930054, "max": 86.58299769461155, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3317784430888984, "min": -1.0000000521540642, "max": 1.3320461183786392, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 86.56559880077839, "min": -32.000001668930054, "max": 86.58299769461155, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.054127485288504085, "min": 0.054127485288504085, "max": 11.316670830635463, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5182865437527653, "min": 3.5182865437527653, "max": 192.38340412080288, "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": "1697078894", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697082079" }, "total": 3185.2569319990002, "count": 1, "self": 0.8846181320004689, "children": { "run_training.setup": { "total": 0.05522893300002352, "count": 1, "self": 0.05522893300002352 }, "TrainerController.start_learning": { "total": 3184.317084934, "count": 1, "self": 2.2248115750012403, "children": { "TrainerController._reset_env": { "total": 1.1492572679999853, "count": 1, "self": 1.1492572679999853 }, "TrainerController.advance": { "total": 3180.816438613999, "count": 63491, "self": 2.3292886979961622, "children": { "env_step": { "total": 2100.423073387011, "count": 63491, "self": 1949.8338545579484, "children": { "SubprocessEnvManager._take_step": { "total": 149.24951739701152, "count": 63491, "self": 6.961477949949142, "children": { "TorchPolicy.evaluate": { "total": 142.28803944706237, "count": 62553, "self": 142.28803944706237 } } }, "workers": { "total": 1.3397014320510152, "count": 63491, "self": 0.0, "children": { "worker_root": { "total": 3177.9428118959295, "count": 63491, "is_parallel": true, "self": 1398.4614989999384, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00552499700000908, "count": 1, "is_parallel": true, "self": 0.003963348000127098, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015616489998819816, "count": 8, "is_parallel": true, "self": 0.0015616489998819816 } } }, "UnityEnvironment.step": { "total": 0.06099987800001827, "count": 1, "is_parallel": true, "self": 0.000681524000015088, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003872560000104386, "count": 1, "is_parallel": true, "self": 0.0003872560000104386 }, "communicator.exchange": { "total": 0.05795901999999842, "count": 1, "is_parallel": true, "self": 0.05795901999999842 }, "steps_from_proto": { "total": 0.001972077999994326, "count": 1, "is_parallel": true, "self": 0.000413078999940808, "children": { "_process_rank_one_or_two_observation": { "total": 0.001558999000053518, "count": 8, "is_parallel": true, "self": 0.001558999000053518 } } } } } } }, "UnityEnvironment.step": { "total": 1779.481312895991, "count": 63490, "is_parallel": true, "self": 46.46474271799002, "children": { "UnityEnvironment._generate_step_input": { "total": 26.786962413955735, "count": 63490, "is_parallel": true, "self": 26.786962413955735 }, "communicator.exchange": { "total": 1577.8154745120353, "count": 63490, "is_parallel": true, "self": 1577.8154745120353 }, "steps_from_proto": { "total": 128.41413325201, "count": 63490, "is_parallel": true, "self": 27.594017199974076, "children": { "_process_rank_one_or_two_observation": { "total": 100.82011605203593, "count": 507920, "is_parallel": true, "self": 100.82011605203593 } } } } } } } } } } }, "trainer_advance": { "total": 1078.064076528992, "count": 63491, "self": 4.136871907974182, "children": { "process_trajectory": { "total": 153.4832396480196, "count": 63491, "self": 153.08848823701982, "children": { "RLTrainer._checkpoint": { "total": 0.3947514109997883, "count": 2, "self": 0.3947514109997883 } } }, "_update_policy": { "total": 920.4439649729982, "count": 443, "self": 356.34656640999833, "children": { "TorchPPOOptimizer.update": { "total": 564.0973985629998, "count": 22797, "self": 564.0973985629998 } } } } } } }, "trainer_threads": { "total": 1.711000095383497e-06, "count": 1, "self": 1.711000095383497e-06 }, "TrainerController._save_models": { "total": 0.12657576599985987, "count": 1, "self": 0.002331227000013314, "children": { "RLTrainer._checkpoint": { "total": 0.12424453899984655, "count": 1, "self": 0.12424453899984655 } } } } } } }