{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.40009623765945435, "min": 0.3948191702365875, "max": 1.4134787321090698, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12169.3271484375, "min": 11695.3251953125, "max": 42879.2890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989957.0, "min": 29952.0, "max": 989957.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989957.0, "min": 29952.0, "max": 989957.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.506927490234375, "min": -0.0909978523850441, "max": 0.506927490234375, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 138.89813232421875, "min": -22.021480560302734, "max": 139.1622314453125, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02838033065199852, "min": -0.03698648139834404, "max": 0.3912530243396759, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.776210784912109, "min": -9.91237735748291, "max": 93.90072631835938, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06646728327628112, "min": 0.0657212955474677, "max": 0.07347887786919204, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9305419658679358, "min": 0.49038713882595636, "max": 1.0783392926872086, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01676727404438203, "min": 0.0009343541404591315, "max": 0.01676727404438203, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23474183662134845, "min": 0.007107377546795217, "max": 0.23474183662134845, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.247454727071432e-06, "min": 7.247454727071432e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010146436617900005, "min": 0.00010146436617900005, "max": 0.0035078066307312, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241578571428571, "min": 0.10241578571428571, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.433821, "min": 1.3691136000000002, "max": 2.5692687999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025133699285714297, "min": 0.00025133699285714297, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003518717900000002, "min": 0.003518717900000002, "max": 0.11694995311999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012660627253353596, "min": 0.012660627253353596, "max": 0.6218632459640503, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1772487759590149, "min": 0.1772487759590149, "max": 4.3530426025390625, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 370.69135802469134, "min": 368.72151898734177, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30026.0, "min": 15984.0, "max": 33364.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.530508623171, "min": -1.0000000521540642, "max": 1.5806328871204882, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 123.97119847685099, "min": -32.000001668930054, "max": 124.86999808251858, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.530508623171, "min": -1.0000000521540642, "max": 1.5806328871204882, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 123.97119847685099, "min": -32.000001668930054, "max": 124.86999808251858, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.048610919323695226, "min": 0.048610919323695226, "max": 12.266703136265278, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.9374844652193133, "min": 3.9374844652193133, "max": 196.26725018024445, "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": "1692521954", "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", "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": "1692524329" }, "total": 2374.510516663, "count": 1, "self": 0.9335381350001626, "children": { "run_training.setup": { "total": 0.03986288900000545, "count": 1, "self": 0.03986288900000545 }, "TrainerController.start_learning": { "total": 2373.537115639, "count": 1, "self": 1.7931507070825319, "children": { "TrainerController._reset_env": { "total": 4.071676476999983, "count": 1, "self": 4.071676476999983 }, "TrainerController.advance": { "total": 2367.512279106918, "count": 63731, "self": 1.6975312269005371, "children": { "env_step": { "total": 1664.4532594469733, "count": 63731, "self": 1533.9117891720018, "children": { "SubprocessEnvManager._take_step": { "total": 129.47971475993995, "count": 63731, "self": 5.267543160959576, "children": { "TorchPolicy.evaluate": { "total": 124.21217159898038, "count": 62565, "self": 124.21217159898038 } } }, "workers": { "total": 1.0617555150315638, "count": 63731, "self": 0.0, "children": { "worker_root": { "total": 2366.881553449046, "count": 63731, "is_parallel": true, "self": 963.8113369070772, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018484770000668505, "count": 1, "is_parallel": true, "self": 0.0005916710001656611, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012568059999011894, "count": 8, "is_parallel": true, "self": 0.0012568059999011894 } } }, "UnityEnvironment.step": { "total": 0.048113227000158076, "count": 1, "is_parallel": true, "self": 0.0005788980001852906, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004992510000647599, "count": 1, "is_parallel": true, "self": 0.0004992510000647599 }, "communicator.exchange": { "total": 0.04513434499995128, "count": 1, "is_parallel": true, "self": 0.04513434499995128 }, "steps_from_proto": { "total": 0.0019007329999567446, "count": 1, "is_parallel": true, "self": 0.0003761449997909949, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015245880001657497, "count": 8, "is_parallel": true, "self": 0.0015245880001657497 } } } } } } }, "UnityEnvironment.step": { "total": 1403.0702165419686, "count": 63730, "is_parallel": true, "self": 36.585841997967464, "children": { "UnityEnvironment._generate_step_input": { "total": 24.16256615095108, "count": 63730, "is_parallel": true, "self": 24.16256615095108 }, "communicator.exchange": { "total": 1227.8734251930525, "count": 63730, "is_parallel": true, "self": 1227.8734251930525 }, "steps_from_proto": { "total": 114.44838319999758, "count": 63730, "is_parallel": true, "self": 23.042838215083975, "children": { "_process_rank_one_or_two_observation": { "total": 91.4055449849136, "count": 509840, "is_parallel": true, "self": 91.4055449849136 } } } } } } } } } } }, "trainer_advance": { "total": 701.3614884330441, "count": 63731, "self": 3.3463133580851263, "children": { "process_trajectory": { "total": 118.72879001396518, "count": 63731, "self": 118.40054231596537, "children": { "RLTrainer._checkpoint": { "total": 0.3282476979998137, "count": 2, "self": 0.3282476979998137 } } }, "_update_policy": { "total": 579.2863850609938, "count": 450, "self": 376.270701794042, "children": { "TorchPPOOptimizer.update": { "total": 203.01568326695178, "count": 22773, "self": 203.01568326695178 } } } } } } }, "trainer_threads": { "total": 1.4929996723367367e-06, "count": 1, "self": 1.4929996723367367e-06 }, "TrainerController._save_models": { "total": 0.16000785500000347, "count": 1, "self": 0.001984326999718178, "children": { "RLTrainer._checkpoint": { "total": 0.1580235280002853, "count": 1, "self": 0.1580235280002853 } } } } } } }