{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4989953339099884, "min": 0.4912518858909607, "max": 1.4354182481765747, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 14953.892578125, "min": 14729.6962890625, "max": 43544.84765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989890.0, "min": 29952.0, "max": 989890.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989890.0, "min": 29952.0, "max": 989890.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.180868461728096, "min": -0.1117670014500618, "max": 0.1819244921207428, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 45.75971984863281, "min": -26.935848236083984, "max": 45.844970703125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1579555869102478, "min": -0.0030871748458594084, "max": 0.3947230577468872, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 39.962764739990234, "min": -0.7656193375587463, "max": 93.54936218261719, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06726911957627613, "min": 0.06443029891826361, "max": 0.07412499049505207, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9417676740678658, "min": 0.513515466926372, "max": 1.0793575286262043, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01450570668751244, "min": 0.00018235658670395408, "max": 0.01450570668751244, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20307989362517415, "min": 0.002370635627151403, "max": 0.20307989362517415, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.765983125657145e-06, "min": 7.765983125657145e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010872376375920002, "min": 0.00010872376375920002, "max": 0.0033827756724082, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258862857142859, "min": 0.10258862857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4362408000000002, "min": 1.3886848, "max": 2.5275917999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002686039942857144, "min": 0.0002686039942857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037604559200000013, "min": 0.0037604559200000013, "max": 0.11278642082000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009434542618691921, "min": 0.009434542618691921, "max": 0.4227748513221741, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13208359479904175, "min": 0.13208359479904175, "max": 2.9594240188598633, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 643.9111111111112, "min": 643.9111111111112, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28976.0, "min": 15984.0, "max": 33132.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.7829869250240533, "min": -1.0000000521540642, "max": 0.9001511835106989, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 36.01739855110645, "min": -29.996001563966274, "max": 36.906198523938656, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.7829869250240533, "min": -1.0000000521540642, "max": 0.9001511835106989, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 36.01739855110645, "min": -29.996001563966274, "max": 36.906198523938656, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06428283193330887, "min": 0.06428283193330887, "max": 8.900084225460887, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9570102689322084, "min": 2.864719823352061, "max": 142.4013476073742, "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": "1714817372", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714820488" }, "total": 3116.7177560889995, "count": 1, "self": 0.5847939289988062, "children": { "run_training.setup": { "total": 0.06742899500000021, "count": 1, "self": 0.06742899500000021 }, "TrainerController.start_learning": { "total": 3116.0655331650005, "count": 1, "self": 2.2741767080387945, "children": { "TrainerController._reset_env": { "total": 2.762040126999864, "count": 1, "self": 2.762040126999864 }, "TrainerController.advance": { "total": 3110.942598192962, "count": 63306, "self": 2.375136069058044, "children": { "env_step": { "total": 2021.1930645039695, "count": 63306, "self": 1857.2817258459052, "children": { "SubprocessEnvManager._take_step": { "total": 162.51026569699638, "count": 63306, "self": 6.995850344825158, "children": { "TorchPolicy.evaluate": { "total": 155.51441535217123, "count": 62568, "self": 155.51441535217123 } } }, "workers": { "total": 1.401072961067939, "count": 63306, "self": 0.0, "children": { "worker_root": { "total": 3109.0966942440004, "count": 63306, "is_parallel": true, "self": 1432.991955369004, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0030358279998381477, "count": 1, "is_parallel": true, "self": 0.0009547610002300644, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020810669996080833, "count": 8, "is_parallel": true, "self": 0.0020810669996080833 } } }, "UnityEnvironment.step": { "total": 0.060320873000137, "count": 1, "is_parallel": true, "self": 0.0007952629998726479, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005512990001079743, "count": 1, "is_parallel": true, "self": 0.0005512990001079743 }, "communicator.exchange": { "total": 0.056853074000173365, "count": 1, "is_parallel": true, "self": 0.056853074000173365 }, "steps_from_proto": { "total": 0.0021212369999830116, "count": 1, "is_parallel": true, "self": 0.00044455599982029526, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016766810001627164, "count": 8, "is_parallel": true, "self": 0.0016766810001627164 } } } } } } }, "UnityEnvironment.step": { "total": 1676.1047388749964, "count": 63305, "is_parallel": true, "self": 50.00227163999875, "children": { "UnityEnvironment._generate_step_input": { "total": 30.899932914918736, "count": 63305, "is_parallel": true, "self": 30.899932914918736 }, "communicator.exchange": { "total": 1465.408956475023, "count": 63305, "is_parallel": true, "self": 1465.408956475023 }, "steps_from_proto": { "total": 129.793577845056, "count": 63305, "is_parallel": true, "self": 27.607772091843344, "children": { "_process_rank_one_or_two_observation": { "total": 102.18580575321266, "count": 506440, "is_parallel": true, "self": 102.18580575321266 } } } } } } } } } } }, "trainer_advance": { "total": 1087.3743976199348, "count": 63306, "self": 4.497276349955655, "children": { "process_trajectory": { "total": 163.70859661498935, "count": 63306, "self": 163.5154260119898, "children": { "RLTrainer._checkpoint": { "total": 0.19317060299954392, "count": 2, "self": 0.19317060299954392 } } }, "_update_policy": { "total": 919.1685246549898, "count": 448, "self": 367.2238264730024, "children": { "TorchPPOOptimizer.update": { "total": 551.9446981819874, "count": 22713, "self": 551.9446981819874 } } } } } } }, "trainer_threads": { "total": 1.1539996194187552e-06, "count": 1, "self": 1.1539996194187552e-06 }, "TrainerController._save_models": { "total": 0.08671698299986019, "count": 1, "self": 0.002222507999249501, "children": { "RLTrainer._checkpoint": { "total": 0.08449447500061069, "count": 1, "self": 0.08449447500061069 } } } } } } }