{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4495241343975067, "min": 0.4495241343975067, "max": 1.4107767343521118, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13478.53125, "min": 13478.53125, "max": 42797.32421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989995.0, "min": 29952.0, "max": 989995.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989995.0, "min": 29952.0, "max": 989995.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3199256956577301, "min": -0.08130579441785812, "max": 0.3199256956577301, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 83.5006103515625, "min": -19.676002502441406, "max": 83.5006103515625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0180850587785244, "min": 0.0006728796870447695, "max": 0.3361949920654297, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.720200538635254, "min": 0.1675470471382141, "max": 80.68679809570312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06628215778767424, "min": 0.06394020384357732, "max": 0.07302285941087458, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9942323668151135, "min": 0.4814984543719356, "max": 1.0738428410544407, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013175696299755275, "min": 0.0005585108496509214, "max": 0.013542283681869908, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19763544449632914, "min": 0.007260641045461977, "max": 0.19763544449632914, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.462217512626665e-06, "min": 7.462217512626665e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011193326268939998, "min": 0.00011193326268939998, "max": 0.0035072120309293997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248737333333333, "min": 0.10248737333333333, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373105999999999, "min": 1.3691136000000002, "max": 2.5690706000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025848859599999997, "min": 0.00025848859599999997, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00387732894, "min": 0.00387732894, "max": 0.11693015294, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01532258652150631, "min": 0.014946640469133854, "max": 0.4283177852630615, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2298388034105301, "min": 0.2092529684305191, "max": 2.9982244968414307, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 489.135593220339, "min": 489.135593220339, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28859.0, "min": 15984.0, "max": 32462.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3074033697277814, "min": -1.0000000521540642, "max": 1.3074033697277814, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 77.1367988139391, "min": -32.000001668930054, "max": 77.1367988139391, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3074033697277814, "min": -1.0000000521540642, "max": 1.3074033697277814, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 77.1367988139391, "min": -32.000001668930054, "max": 77.1367988139391, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07710601762825055, "min": 0.07710601762825055, "max": 8.001284336671233, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.549255040066782, "min": 4.549255040066782, "max": 128.02054938673973, "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": "1703355890", "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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703356707" }, "total": 817.4904990239993, "count": 1, "self": 0.2183181769978546, "children": { "run_training.setup": { "total": 0.032905594001931604, "count": 1, "self": 0.032905594001931604 }, "TrainerController.start_learning": { "total": 817.2392752529995, "count": 1, "self": 0.7701829648831335, "children": { "TrainerController._reset_env": { "total": 1.3251133289995778, "count": 1, "self": 1.3251133289995778 }, "TrainerController.advance": { "total": 815.0917670321178, "count": 63410, "self": 0.7577973998231755, "children": { "env_step": { "total": 482.47640340685757, "count": 63410, "self": 411.401752186026, "children": { "SubprocessEnvManager._take_step": { "total": 70.5956241194217, "count": 63410, "self": 2.296619458564237, "children": { "TorchPolicy.evaluate": { "total": 68.29900466085746, "count": 62556, "self": 68.29900466085746 } } }, "workers": { "total": 0.47902710140988347, "count": 63410, "self": 0.0, "children": { "worker_root": { "total": 816.2783734252189, "count": 63410, "is_parallel": true, "self": 455.7166669260405, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009717610009829514, "count": 1, "is_parallel": true, "self": 0.0002676410076674074, "children": { "_process_rank_one_or_two_observation": { "total": 0.000704119993315544, "count": 8, "is_parallel": true, "self": 0.000704119993315544 } } }, "UnityEnvironment.step": { "total": 0.018779147998429835, "count": 1, "is_parallel": true, "self": 0.00019674999202834442, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017820300126913935, "count": 1, "is_parallel": true, "self": 0.00017820300126913935 }, "communicator.exchange": { "total": 0.017752720003045397, "count": 1, "is_parallel": true, "self": 0.017752720003045397 }, "steps_from_proto": { "total": 0.0006514750020869542, "count": 1, "is_parallel": true, "self": 0.0001506970038462896, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005007779982406646, "count": 8, "is_parallel": true, "self": 0.0005007779982406646 } } } } } } }, "UnityEnvironment.step": { "total": 360.5617064991784, "count": 63409, "is_parallel": true, "self": 11.287857533818169, "children": { "UnityEnvironment._generate_step_input": { "total": 8.587289858693111, "count": 63409, "is_parallel": true, "self": 8.587289858693111 }, "communicator.exchange": { "total": 306.77908012779517, "count": 63409, "is_parallel": true, "self": 306.77908012779517 }, "steps_from_proto": { "total": 33.90747897887195, "count": 63409, "is_parallel": true, "self": 7.941693973622023, "children": { "_process_rank_one_or_two_observation": { "total": 25.965785005249927, "count": 507272, "is_parallel": true, "self": 25.965785005249927 } } } } } } } } } } }, "trainer_advance": { "total": 331.85756622543704, "count": 63410, "self": 1.2808136848871072, "children": { "process_trajectory": { "total": 60.343189832590724, "count": 63410, "self": 60.241326343591936, "children": { "RLTrainer._checkpoint": { "total": 0.10186348899878794, "count": 2, "self": 0.10186348899878794 } } }, "_update_policy": { "total": 270.2335627079592, "count": 445, "self": 151.89631130195266, "children": { "TorchPPOOptimizer.update": { "total": 118.33725140600654, "count": 22791, "self": 118.33725140600654 } } } } } } }, "trainer_threads": { "total": 6.219997885636985e-07, "count": 1, "self": 6.219997885636985e-07 }, "TrainerController._save_models": { "total": 0.052211304999218555, "count": 1, "self": 0.0005980749992886558, "children": { "RLTrainer._checkpoint": { "total": 0.0516132299999299, "count": 1, "self": 0.0516132299999299 } } } } } } }