{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45489737391471863, "min": 0.45489737391471863, "max": 1.4714031219482422, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13574.1376953125, "min": 13574.1376953125, "max": 44636.484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989892.0, "min": 29967.0, "max": 989892.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989892.0, "min": 29967.0, "max": 989892.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4030586779117584, "min": -0.11353225260972977, "max": 0.4030586779117584, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 107.21360778808594, "min": -27.247739791870117, "max": 107.21360778808594, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.47490787506103516, "min": -0.06995981186628342, "max": 0.47490787506103516, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 126.32549285888672, "min": -18.329471588134766, "max": 126.32549285888672, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06902519759569768, "min": 0.06348962848209166, "max": 0.07315616151774848, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9663527663397676, "min": 0.48413222034454434, "max": 1.0701530129447872, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0337037317944281, "min": 0.0006289413212094127, "max": 0.0337037317944281, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.4718522451219934, "min": 0.00691835453330354, "max": 0.4718522451219934, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.6034474655499984e-06, "min": 7.6034474655499984e-06, "max": 0.00029523775873027143, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010644826451769997, "min": 0.00010644826451769997, "max": 0.0034915507361498, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253445000000003, "min": 0.10253445000000003, "max": 0.19841258571428572, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4354823000000003, "min": 1.3888881, "max": 2.482534, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002631915549999999, "min": 0.0002631915549999999, "max": 0.009841417312857143, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003684681769999999, "min": 0.003684681769999999, "max": 0.11639863498, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008070657961070538, "min": 0.008070657961070538, "max": 0.5271876454353333, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11298920959234238, "min": 0.11298920959234238, "max": 3.6903135776519775, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 475.97058823529414, "min": 442.953125, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32366.0, "min": 16510.0, "max": 32549.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2886558577199192, "min": -1.0000000521540642, "max": 1.3805787698789076, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 87.62859832495451, "min": -32.000001668930054, "max": 91.1181988120079, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2886558577199192, "min": -1.0000000521540642, "max": 1.3805787698789076, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 87.62859832495451, "min": -32.000001668930054, "max": 91.1181988120079, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03921399086453568, "min": 0.03888371785814386, "max": 10.18365011057433, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.6665513787884265, "min": 2.449674225063063, "max": 173.1220518797636, "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": "1729333452", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1729337014" }, "total": 3561.748734714, "count": 1, "self": 0.6550481559993386, "children": { "run_training.setup": { "total": 0.07349279200002456, "count": 1, "self": 0.07349279200002456 }, "TrainerController.start_learning": { "total": 3561.0201937660004, "count": 1, "self": 2.7081672220433575, "children": { "TrainerController._reset_env": { "total": 6.67509678600004, "count": 1, "self": 6.67509678600004 }, "TrainerController.advance": { "total": 3551.5438725729573, "count": 63537, "self": 2.672897847960485, "children": { "env_step": { "total": 2360.629174557999, "count": 63537, "self": 2165.9908483659574, "children": { "SubprocessEnvManager._take_step": { "total": 192.9302995470208, "count": 63537, "self": 7.735234674023104, "children": { "TorchPolicy.evaluate": { "total": 185.1950648729977, "count": 62553, "self": 185.1950648729977 } } }, "workers": { "total": 1.7080266450207091, "count": 63537, "self": 0.0, "children": { "worker_root": { "total": 3552.7370987870377, "count": 63537, "is_parallel": true, "self": 1588.2168057279796, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005685286000016276, "count": 1, "is_parallel": true, "self": 0.003411220000089088, "children": { "_process_rank_one_or_two_observation": { "total": 0.0022740659999271884, "count": 8, "is_parallel": true, "self": 0.0022740659999271884 } } }, "UnityEnvironment.step": { "total": 0.06685379199996078, "count": 1, "is_parallel": true, "self": 0.0008712049999530791, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005576620000056209, "count": 1, "is_parallel": true, "self": 0.0005576620000056209 }, "communicator.exchange": { "total": 0.06312194099996304, "count": 1, "is_parallel": true, "self": 0.06312194099996304 }, "steps_from_proto": { "total": 0.0023029840000390323, "count": 1, "is_parallel": true, "self": 0.00047233199984475505, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018306520001942772, "count": 8, "is_parallel": true, "self": 0.0018306520001942772 } } } } } } }, "UnityEnvironment.step": { "total": 1964.520293059058, "count": 63536, "is_parallel": true, "self": 55.046853999984705, "children": { "UnityEnvironment._generate_step_input": { "total": 32.72053381002695, "count": 63536, "is_parallel": true, "self": 32.72053381002695 }, "communicator.exchange": { "total": 1739.19454688804, "count": 63536, "is_parallel": true, "self": 1739.19454688804 }, "steps_from_proto": { "total": 137.5583583610064, "count": 63536, "is_parallel": true, "self": 30.24983618596241, "children": { "_process_rank_one_or_two_observation": { "total": 107.308522175044, "count": 508288, "is_parallel": true, "self": 107.308522175044 } } } } } } } } } } }, "trainer_advance": { "total": 1188.2418001669982, "count": 63537, "self": 5.5230490939732135, "children": { "process_trajectory": { "total": 183.56295144701915, "count": 63537, "self": 183.23390894001966, "children": { "RLTrainer._checkpoint": { "total": 0.32904250699948534, "count": 2, "self": 0.32904250699948534 } } }, "_update_policy": { "total": 999.1557996260059, "count": 451, "self": 395.0297264079478, "children": { "TorchPPOOptimizer.update": { "total": 604.1260732180581, "count": 22782, "self": 604.1260732180581 } } } } } } }, "trainer_threads": { "total": 1.2279997463338077e-06, "count": 1, "self": 1.2279997463338077e-06 }, "TrainerController._save_models": { "total": 0.09305595700016056, "count": 1, "self": 0.0024269569998978113, "children": { "RLTrainer._checkpoint": { "total": 0.09062900000026275, "count": 1, "self": 0.09062900000026275 } } } } } } }