{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41119223833084106, "min": 0.41119223833084106, "max": 1.471925973892212, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12151.552734375, "min": 12151.552734375, "max": 44652.34765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989883.0, "min": 29952.0, "max": 989883.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989883.0, "min": 29952.0, "max": 989883.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.427590012550354, "min": -0.31348738074302673, "max": 0.5430094003677368, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 113.31135559082031, "min": -74.2965087890625, "max": 150.41360473632812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.030404971912503242, "min": -0.011679602786898613, "max": 0.35483700037002563, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.057317733764648, "min": -3.1184539794921875, "max": 85.16088104248047, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06963869239373527, "min": 0.06418292059690567, "max": 0.07342489732537676, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9749416935122938, "min": 0.5139742812776373, "max": 1.0415133859085686, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014876755937567558, "min": 0.00016056364700314042, "max": 0.016039063518941736, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20827458312594582, "min": 0.0020873274110408254, "max": 0.2245468892651843, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.750233130907146e-06, "min": 7.750233130907146e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010850326383270003, "min": 0.00010850326383270003, "max": 0.0036090432969856, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258337857142859, "min": 0.10258337857142859, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4361673000000001, "min": 1.3886848, "max": 2.569091400000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002680795192857144, "min": 0.0002680795192857144, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003753113270000002, "min": 0.003753113270000002, "max": 0.12031113856, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013370824977755547, "min": 0.013067224994301796, "max": 0.44320252537727356, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18719154596328735, "min": 0.18294115364551544, "max": 3.1024177074432373, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 431.6857142857143, "min": 359.5365853658537, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30218.0, "min": 15984.0, "max": 33444.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4825685461716993, "min": -1.0000000521540642, "max": 1.5938626305166497, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 103.77979823201895, "min": -31.99320162832737, "max": 132.29059833288193, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4825685461716993, "min": -1.0000000521540642, "max": 1.5938626305166497, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 103.77979823201895, "min": -31.99320162832737, "max": 132.29059833288193, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06012799181376717, "min": 0.047820723676599605, "max": 9.20178209245205, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.208959426963702, "min": 3.9691200651577674, "max": 147.2285134792328, "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": "1716267205", "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": "1716270872" }, "total": 3666.491618387001, "count": 1, "self": 0.6056720080014202, "children": { "run_training.setup": { "total": 0.08369009099988034, "count": 1, "self": 0.08369009099988034 }, "TrainerController.start_learning": { "total": 3665.8022562879996, "count": 1, "self": 2.5587414731307945, "children": { "TrainerController._reset_env": { "total": 4.3099131639992265, "count": 1, "self": 4.3099131639992265 }, "TrainerController.advance": { "total": 3658.8384550078717, "count": 63591, "self": 2.6622956246756075, "children": { "env_step": { "total": 2455.0247556050854, "count": 63591, "self": 2269.795731178263, "children": { "SubprocessEnvManager._take_step": { "total": 183.6438605799558, "count": 63591, "self": 8.054882045929844, "children": { "TorchPolicy.evaluate": { "total": 175.58897853402596, "count": 62569, "self": 175.58897853402596 } } }, "workers": { "total": 1.5851638468666351, "count": 63591, "self": 0.0, "children": { "worker_root": { "total": 3658.4097298003308, "count": 63591, "is_parallel": true, "self": 1598.6894520580572, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0034536969997134292, "count": 1, "is_parallel": true, "self": 0.0011708140027621994, "children": { "_process_rank_one_or_two_observation": { "total": 0.00228288299695123, "count": 8, "is_parallel": true, "self": 0.00228288299695123 } } }, "UnityEnvironment.step": { "total": 0.07880420999936177, "count": 1, "is_parallel": true, "self": 0.0009447929987800308, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003980229994340334, "count": 1, "is_parallel": true, "self": 0.0003980229994340334 }, "communicator.exchange": { "total": 0.07514179099962348, "count": 1, "is_parallel": true, "self": 0.07514179099962348 }, "steps_from_proto": { "total": 0.0023196030015242286, "count": 1, "is_parallel": true, "self": 0.0004996620009478647, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018199410005763639, "count": 8, "is_parallel": true, "self": 0.0018199410005763639 } } } } } } }, "UnityEnvironment.step": { "total": 2059.7202777422735, "count": 63590, "is_parallel": true, "self": 54.83721629233514, "children": { "UnityEnvironment._generate_step_input": { "total": 30.524886827221053, "count": 63590, "is_parallel": true, "self": 30.524886827221053 }, "communicator.exchange": { "total": 1835.700426211004, "count": 63590, "is_parallel": true, "self": 1835.700426211004 }, "steps_from_proto": { "total": 138.65774841171333, "count": 63590, "is_parallel": true, "self": 30.40246924056919, "children": { "_process_rank_one_or_two_observation": { "total": 108.25527917114414, "count": 508720, "is_parallel": true, "self": 108.25527917114414 } } } } } } } } } } }, "trainer_advance": { "total": 1201.1514037781108, "count": 63591, "self": 5.0563354261230415, "children": { "process_trajectory": { "total": 186.4566107019691, "count": 63591, "self": 186.15627448797022, "children": { "RLTrainer._checkpoint": { "total": 0.30033621399888943, "count": 2, "self": 0.30033621399888943 } } }, "_update_policy": { "total": 1009.6384576500186, "count": 453, "self": 395.337199764821, "children": { "TorchPPOOptimizer.update": { "total": 614.3012578851976, "count": 22749, "self": 614.3012578851976 } } } } } } }, "trainer_threads": { "total": 1.2519994925241917e-06, "count": 1, "self": 1.2519994925241917e-06 }, "TrainerController._save_models": { "total": 0.09514539099836838, "count": 1, "self": 0.001965040997674805, "children": { "RLTrainer._checkpoint": { "total": 0.09318035000069358, "count": 1, "self": 0.09318035000069358 } } } } } } }