{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.43318936228752136, "min": 0.4141612946987152, "max": 1.4639779329299927, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13030.3359375, "min": 12424.8388671875, "max": 44411.234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989932.0, "min": 29952.0, "max": 989932.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989932.0, "min": 29952.0, "max": 989932.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5808075666427612, "min": -0.10350541770458221, "max": 0.6455045342445374, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.62611389160156, "min": -24.944805145263672, "max": 183.3232879638672, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013156615197658539, "min": -0.015836521983146667, "max": 0.37826859951019287, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.683852195739746, "min": -4.513408660888672, "max": 89.649658203125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06587783050310785, "min": 0.06437641343216643, "max": 0.07436352533445795, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9222896270435099, "min": 0.48551582701148965, "max": 1.0630589033098659, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015399283060085136, "min": 0.00012594139234651548, "max": 0.017571093799363422, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21558996284119192, "min": 0.0016372381005047014, "max": 0.24922233681233288, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5631403361285705e-06, "min": 7.5631403361285705e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010588396470579999, "min": 0.00010588396470579999, "max": 0.0032245849251383994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252101428571427, "min": 0.10252101428571427, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352941999999997, "min": 1.3886848, "max": 2.4434626000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002618493271428571, "min": 0.0002618493271428571, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036658905799999996, "min": 0.0036658905799999996, "max": 0.10749867384, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008430602960288525, "min": 0.008319594897329807, "max": 0.44083473086357117, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11802844703197479, "min": 0.11647433042526245, "max": 3.085843086242676, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 319.65555555555557, "min": 302.7669902912621, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28769.0, "min": 15984.0, "max": 32658.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.636083498269647, "min": -1.0000000521540642, "max": 1.6780783411153812, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 148.88359834253788, "min": -31.99920167028904, "max": 170.98839837312698, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.636083498269647, "min": -1.0000000521540642, "max": 1.6780783411153812, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 148.88359834253788, "min": -31.99920167028904, "max": 170.98839837312698, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02808619650462348, "min": 0.025916771017222947, "max": 9.93404626660049, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5558438819207367, "min": 2.5558438819207367, "max": 158.94474026560783, "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": "1693297889", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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 --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1693301194" }, "total": 3305.025149788, "count": 1, "self": 0.5873024080001414, "children": { "run_training.setup": { "total": 0.03932263100000455, "count": 1, "self": 0.03932263100000455 }, "TrainerController.start_learning": { "total": 3304.398524749, "count": 1, "self": 2.5172201100340317, "children": { "TrainerController._reset_env": { "total": 1.3596174319999932, "count": 1, "self": 1.3596174319999932 }, "TrainerController.advance": { "total": 3300.4482201299656, "count": 63914, "self": 2.442539800956638, "children": { "env_step": { "total": 1953.5753315520033, "count": 63914, "self": 1785.7134670379658, "children": { "SubprocessEnvManager._take_step": { "total": 166.23750759302538, "count": 63914, "self": 6.347456428032331, "children": { "TorchPolicy.evaluate": { "total": 159.89005116499305, "count": 62552, "self": 159.89005116499305 } } }, "workers": { "total": 1.6243569210120654, "count": 63914, "self": 0.0, "children": { "worker_root": { "total": 3297.4300507349644, "count": 63914, "is_parallel": true, "self": 1682.7214375929016, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008229859999971723, "count": 1, "is_parallel": true, "self": 0.006582329999957892, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016475300000138304, "count": 8, "is_parallel": true, "self": 0.0016475300000138304 } } }, "UnityEnvironment.step": { "total": 0.06233935199998086, "count": 1, "is_parallel": true, "self": 0.0005450799999948686, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005350199999725191, "count": 1, "is_parallel": true, "self": 0.0005350199999725191 }, "communicator.exchange": { "total": 0.059455552000031275, "count": 1, "is_parallel": true, "self": 0.059455552000031275 }, "steps_from_proto": { "total": 0.0018036999999822, "count": 1, "is_parallel": true, "self": 0.0003838199999108838, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014198800000713163, "count": 8, "is_parallel": true, "self": 0.0014198800000713163 } } } } } } }, "UnityEnvironment.step": { "total": 1614.7086131420629, "count": 63913, "is_parallel": true, "self": 39.054732416005436, "children": { "UnityEnvironment._generate_step_input": { "total": 24.307553316041435, "count": 63913, "is_parallel": true, "self": 24.307553316041435 }, "communicator.exchange": { "total": 1434.6050505060132, "count": 63913, "is_parallel": true, "self": 1434.6050505060132 }, "steps_from_proto": { "total": 116.74127690400275, "count": 63913, "is_parallel": true, "self": 25.91737872301121, "children": { "_process_rank_one_or_two_observation": { "total": 90.82389818099153, "count": 511304, "is_parallel": true, "self": 90.82389818099153 } } } } } } } } } } }, "trainer_advance": { "total": 1344.4303487770055, "count": 63914, "self": 5.235813993986994, "children": { "process_trajectory": { "total": 153.52240422201857, "count": 63914, "self": 153.3201436540184, "children": { "RLTrainer._checkpoint": { "total": 0.20226056800015613, "count": 2, "self": 0.20226056800015613 } } }, "_update_policy": { "total": 1185.672130561, "count": 447, "self": 344.3032888279698, "children": { "TorchPPOOptimizer.update": { "total": 841.3688417330301, "count": 22818, "self": 841.3688417330301 } } } } } } }, "trainer_threads": { "total": 8.700003490957897e-07, "count": 1, "self": 8.700003490957897e-07 }, "TrainerController._save_models": { "total": 0.07346620699991036, "count": 1, "self": 0.0011724999999387364, "children": { "RLTrainer._checkpoint": { "total": 0.07229370699997162, "count": 1, "self": 0.07229370699997162 } } } } } } }