{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43407079577445984, "min": 0.42527782917022705, "max": 1.4837955236434937, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12904.056640625, "min": 12737.921875, "max": 45012.421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989911.0, "min": 29952.0, "max": 989911.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989911.0, "min": 29952.0, "max": 989911.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5767265558242798, "min": -0.16844777762889862, "max": 0.612508237361908, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 158.0230712890625, "min": -39.922122955322266, "max": 170.88980102539062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.00850876234471798, "min": -0.03281579911708832, "max": 0.3009519577026367, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.3314008712768555, "min": -8.860265731811523, "max": 72.5294189453125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06775942262278736, "min": 0.06507797840886805, "max": 0.0718982202711881, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9486319167190231, "min": 0.491452663355432, "max": 1.065007424719321, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015864644856524786, "min": 0.0006806989169103642, "max": 0.0172680757417414, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.222105027991347, "min": 0.008849085919834736, "max": 0.2417530603843796, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4504475165499995e-06, "min": 7.4504475165499995e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010430626523169999, "min": 0.00010430626523169999, "max": 0.0033817955727349, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248345000000002, "min": 0.10248345000000002, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347683000000002, "min": 1.3886848, "max": 2.5272651, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025809665500000007, "min": 0.00025809665500000007, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036133531700000008, "min": 0.0036133531700000008, "max": 0.11275378348999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010653096251189709, "min": 0.010653096251189709, "max": 0.43323490023612976, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14914335310459137, "min": 0.14914335310459137, "max": 3.032644271850586, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 325.7977528089888, "min": 288.0, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28996.0, "min": 15984.0, "max": 33925.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.651721326990074, "min": -1.0000000521540642, "max": 1.651721326990074, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 147.00319810211658, "min": -28.266001626849174, "max": 171.9449976682663, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.651721326990074, "min": -1.0000000521540642, "max": 1.651721326990074, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 147.00319810211658, "min": -28.266001626849174, "max": 171.9449976682663, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.035411360995220076, "min": 0.035411360995220076, "max": 8.571720628067851, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1516111285745865, "min": 3.1516111285745865, "max": 137.14753004908562, "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": "1754575990", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1754578211" }, "total": 2221.377463368, "count": 1, "self": 0.7650903400003699, "children": { "run_training.setup": { "total": 0.027368948999992426, "count": 1, "self": 0.027368948999992426 }, "TrainerController.start_learning": { "total": 2220.5850040789996, "count": 1, "self": 1.346251471067717, "children": { "TrainerController._reset_env": { "total": 2.5212945329999457, "count": 1, "self": 2.5212945329999457 }, "TrainerController.advance": { "total": 2216.6031353579324, "count": 63944, "self": 1.3791782740390772, "children": { "env_step": { "total": 1559.7259500259647, "count": 63944, "self": 1415.1660427130223, "children": { "SubprocessEnvManager._take_step": { "total": 143.7468732469597, "count": 63944, "self": 4.429113454985327, "children": { "TorchPolicy.evaluate": { "total": 139.31775979197437, "count": 62550, "self": 139.31775979197437 } } }, "workers": { "total": 0.8130340659827198, "count": 63944, "self": 0.0, "children": { "worker_root": { "total": 2215.7580473560615, "count": 63944, "is_parallel": true, "self": 910.4688227340862, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025719969999045134, "count": 1, "is_parallel": true, "self": 0.0008216759993047162, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017503210005997971, "count": 8, "is_parallel": true, "self": 0.0017503210005997971 } } }, "UnityEnvironment.step": { "total": 0.05092954599967925, "count": 1, "is_parallel": true, "self": 0.0005536380003832164, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045113899977877736, "count": 1, "is_parallel": true, "self": 0.00045113899977877736 }, "communicator.exchange": { "total": 0.048274782999669696, "count": 1, "is_parallel": true, "self": 0.048274782999669696 }, "steps_from_proto": { "total": 0.0016499859998475586, "count": 1, "is_parallel": true, "self": 0.00036246099898562534, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012875250008619332, "count": 8, "is_parallel": true, "self": 0.0012875250008619332 } } } } } } }, "UnityEnvironment.step": { "total": 1305.2892246219753, "count": 63943, "is_parallel": true, "self": 31.497336503966835, "children": { "UnityEnvironment._generate_step_input": { "total": 22.117139126020902, "count": 63943, "is_parallel": true, "self": 22.117139126020902 }, "communicator.exchange": { "total": 1158.5751216730123, "count": 63943, "is_parallel": true, "self": 1158.5751216730123 }, "steps_from_proto": { "total": 93.09962731897531, "count": 63943, "is_parallel": true, "self": 18.511454564938504, "children": { "_process_rank_one_or_two_observation": { "total": 74.5881727540368, "count": 511544, "is_parallel": true, "self": 74.5881727540368 } } } } } } } } } } }, "trainer_advance": { "total": 655.4980070579286, "count": 63944, "self": 2.587601174887368, "children": { "process_trajectory": { "total": 123.31635473403867, "count": 63944, "self": 123.08747297803893, "children": { "RLTrainer._checkpoint": { "total": 0.22888175599973692, "count": 2, "self": 0.22888175599973692 } } }, "_update_policy": { "total": 529.5940511490026, "count": 449, "self": 294.47535499496325, "children": { "TorchPPOOptimizer.update": { "total": 235.1186961540393, "count": 22776, "self": 235.1186961540393 } } } } } } }, "trainer_threads": { "total": 1.0399999155197293e-06, "count": 1, "self": 1.0399999155197293e-06 }, "TrainerController._save_models": { "total": 0.11432167699967977, "count": 1, "self": 0.0018506549995436217, "children": { "RLTrainer._checkpoint": { "total": 0.11247102200013614, "count": 1, "self": 0.11247102200013614 } } } } } } }