{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3527590036392212, "min": 0.3527590036392212, "max": 1.4888267517089844, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10599.7021484375, "min": 10599.7021484375, "max": 45165.046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989886.0, "min": 29997.0, "max": 989886.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989886.0, "min": 29997.0, "max": 989886.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6520658731460571, "min": -0.09461230039596558, "max": 0.7290874123573303, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 185.83877563476562, "min": -22.51772689819336, "max": 214.35169982910156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008596635423600674, "min": -0.014068011194467545, "max": 0.5574564933776855, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.4500410556793213, "min": -3.8124310970306396, "max": 132.67465209960938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06592145197228652, "min": 0.06485723622046419, "max": 0.07387951720161724, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9229003276120114, "min": 0.5910361376129379, "max": 1.0795506855322268, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016225723004536324, "min": 0.0004137045287184412, "max": 0.01735325380739394, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22716012206350855, "min": 0.005378158873339736, "max": 0.2602988071109091, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.579683187757148e-06, "min": 7.579683187757148e-06, "max": 0.000294762001746, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010611556462860007, "min": 0.00010611556462860007, "max": 0.0036335290888236996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252652857142856, "min": 0.10252652857142856, "max": 0.19825399999999999, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353714, "min": 1.4353714, "max": 2.6111763000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002624002042857144, "min": 0.0002624002042857144, "max": 0.009825574600000001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003673602860000002, "min": 0.003673602860000002, "max": 0.12113651237000003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010128624737262726, "min": 0.010128624737262726, "max": 0.3731467127799988, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14180074632167816, "min": 0.14180074632167816, "max": 2.9851737022399902, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 281.4433962264151, "min": 263.92105263157896, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29833.0, "min": 17435.0, "max": 32592.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6804112013533852, "min": -0.9999125520698726, "max": 1.7369468928174634, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 179.8039985448122, "min": -31.997201666235924, "max": 196.27499888837337, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6804112013533852, "min": -0.9999125520698726, "max": 1.7369468928174634, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 179.8039985448122, "min": -31.997201666235924, "max": 196.27499888837337, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0296619328616892, "min": 0.02769949252946937, "max": 7.453023180365562, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1738268162007444, "min": 3.1300426558300387, "max": 134.15441724658012, "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": "1736913440", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1736916812" }, "total": 3371.844608839, "count": 1, "self": 0.8902623129997664, "children": { "run_training.setup": { "total": 0.07292771700008416, "count": 1, "self": 0.07292771700008416 }, "TrainerController.start_learning": { "total": 3370.881418809, "count": 1, "self": 2.377010063923535, "children": { "TrainerController._reset_env": { "total": 2.705583632000071, "count": 1, "self": 2.705583632000071 }, "TrainerController.advance": { "total": 3365.6715638710766, "count": 64233, "self": 2.5651395729960313, "children": { "env_step": { "total": 2245.7267651930206, "count": 64233, "self": 2080.341739934925, "children": { "SubprocessEnvManager._take_step": { "total": 163.96578919013882, "count": 64233, "self": 7.028983484116679, "children": { "TorchPolicy.evaluate": { "total": 156.93680570602214, "count": 62568, "self": 156.93680570602214 } } }, "workers": { "total": 1.4192360679567173, "count": 64233, "self": 0.0, "children": { "worker_root": { "total": 3363.604147653999, "count": 64233, "is_parallel": true, "self": 1463.0668140029259, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003035490000002028, "count": 1, "is_parallel": true, "self": 0.0010073559997181292, "children": { "_process_rank_one_or_two_observation": { "total": 0.002028134000283899, "count": 8, "is_parallel": true, "self": 0.002028134000283899 } } }, "UnityEnvironment.step": { "total": 0.07518343500009905, "count": 1, "is_parallel": true, "self": 0.0017371960002492415, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005394679999426444, "count": 1, "is_parallel": true, "self": 0.0005394679999426444 }, "communicator.exchange": { "total": 0.06519961499998317, "count": 1, "is_parallel": true, "self": 0.06519961499998317 }, "steps_from_proto": { "total": 0.007707155999923998, "count": 1, "is_parallel": true, "self": 0.0004629539996585663, "children": { "_process_rank_one_or_two_observation": { "total": 0.007244202000265432, "count": 8, "is_parallel": true, "self": 0.007244202000265432 } } } } } } }, "UnityEnvironment.step": { "total": 1900.5373336510731, "count": 64232, "is_parallel": true, "self": 49.02852955310527, "children": { "UnityEnvironment._generate_step_input": { "total": 29.960821111031464, "count": 64232, "is_parallel": true, "self": 29.960821111031464 }, "communicator.exchange": { "total": 1691.9833964239674, "count": 64232, "is_parallel": true, "self": 1691.9833964239674 }, "steps_from_proto": { "total": 129.564586562969, "count": 64232, "is_parallel": true, "self": 27.682482523893214, "children": { "_process_rank_one_or_two_observation": { "total": 101.88210403907578, "count": 513856, "is_parallel": true, "self": 101.88210403907578 } } } } } } } } } } }, "trainer_advance": { "total": 1117.37965910506, "count": 64233, "self": 4.517097864914149, "children": { "process_trajectory": { "total": 168.18864389714213, "count": 64233, "self": 167.8518159171424, "children": { "RLTrainer._checkpoint": { "total": 0.33682797999972536, "count": 2, "self": 0.33682797999972536 } } }, "_update_policy": { "total": 944.6739173430037, "count": 460, "self": 380.94029479700475, "children": { "TorchPPOOptimizer.update": { "total": 563.733622545999, "count": 22767, "self": 563.733622545999 } } } } } } }, "trainer_threads": { "total": 1.6009998944355175e-06, "count": 1, "self": 1.6009998944355175e-06 }, "TrainerController._save_models": { "total": 0.1272596409999096, "count": 1, "self": 0.004123546000300848, "children": { "RLTrainer._checkpoint": { "total": 0.12313609499960876, "count": 1, "self": 0.12313609499960876 } } } } } } }