{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.4391878545284271, "min": 0.41794779896736145, "max": 1.39289391040802, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13154.5546875, "min": 12525.0595703125, "max": 42254.828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989983.0, "min": 29952.0, "max": 989983.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.36080309748649597, "min": -0.09824856370687485, "max": 0.36080309748649597, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 93.80880737304688, "min": -23.67790412902832, "max": 94.2880630493164, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04486580565571785, "min": 0.0038332301191985607, "max": 0.450874000787735, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.665109634399414, "min": 1.0043063163757324, "max": 106.85713958740234, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06930078392144337, "min": 0.06425229468020714, "max": 0.07463606191542022, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9702109749002071, "min": 0.4872680443302921, "max": 1.0419525219893366, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.010651661275395392, "min": 0.00016920833289093773, "max": 0.015199702214999705, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14912325785553548, "min": 0.002030499994691253, "max": 0.22239673477209482, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.283390429378574e-06, "min": 7.283390429378574e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010196746601130003, "min": 0.00010196746601130003, "max": 0.0033762532745822997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1024277642857143, "min": 0.1024277642857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4339887000000002, "min": 1.3886848, "max": 2.4432207, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025253365214285723, "min": 0.00025253365214285723, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035354711300000013, "min": 0.0035354711300000013, "max": 0.11255922823, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010318094864487648, "min": 0.01031502801924944, "max": 0.6120495796203613, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14445333182811737, "min": 0.1444103866815567, "max": 4.284347057342529, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 505.85714285714283, "min": 442.36764705882354, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28328.0, "min": 15984.0, "max": 33764.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3195613705013927, "min": -1.0000000521540642, "max": 1.3786507227749967, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 75.21499811857939, "min": -31.995201647281647, "max": 92.36959842592478, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3195613705013927, "min": -1.0000000521540642, "max": 1.3786507227749967, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 75.21499811857939, "min": -31.995201647281647, "max": 92.36959842592478, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05383677301997842, "min": 0.049256335091292805, "max": 13.50219471566379, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0686960621387698, "min": 3.0686960621387698, "max": 216.03511545062065, "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": "1769209797", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1769211899" }, "total": 2102.082265533, "count": 1, "self": 0.4794251049997911, "children": { "run_training.setup": { "total": 0.022532119000061357, "count": 1, "self": 0.022532119000061357 }, "TrainerController.start_learning": { "total": 2101.580308309, "count": 1, "self": 1.5074309599704065, "children": { "TrainerController._reset_env": { "total": 2.14139627499992, "count": 1, "self": 2.14139627499992 }, "TrainerController.advance": { "total": 2097.8526599940296, "count": 63460, "self": 1.541979396082752, "children": { "env_step": { "total": 1444.8048169729827, "count": 63460, "self": 1288.2826343280703, "children": { "SubprocessEnvManager._take_step": { "total": 155.6027454629384, "count": 63460, "self": 4.805475674950003, "children": { "TorchPolicy.evaluate": { "total": 150.7972697879884, "count": 62560, "self": 150.7972697879884 } } }, "workers": { "total": 0.9194371819738762, "count": 63460, "self": 0.0, "children": { "worker_root": { "total": 2094.948446758984, "count": 63460, "is_parallel": true, "self": 925.3449679729883, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019360850000111895, "count": 1, "is_parallel": true, "self": 0.0005717410000443124, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013643439999668772, "count": 8, "is_parallel": true, "self": 0.0013643439999668772 } } }, "UnityEnvironment.step": { "total": 0.04806159999998272, "count": 1, "is_parallel": true, "self": 0.0006606250000231739, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005053439999755938, "count": 1, "is_parallel": true, "self": 0.0005053439999755938 }, "communicator.exchange": { "total": 0.0451225169999816, "count": 1, "is_parallel": true, "self": 0.0451225169999816 }, "steps_from_proto": { "total": 0.0017731140000023515, "count": 1, "is_parallel": true, "self": 0.00040791499975512124, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013651990002472303, "count": 8, "is_parallel": true, "self": 0.0013651990002472303 } } } } } } }, "UnityEnvironment.step": { "total": 1169.6034787859958, "count": 63459, "is_parallel": true, "self": 33.23648674001697, "children": { "UnityEnvironment._generate_step_input": { "total": 22.35937546100331, "count": 63459, "is_parallel": true, "self": 22.35937546100331 }, "communicator.exchange": { "total": 1009.720432573948, "count": 63459, "is_parallel": true, "self": 1009.720432573948 }, "steps_from_proto": { "total": 104.28718401102742, "count": 63459, "is_parallel": true, "self": 22.173314661068503, "children": { "_process_rank_one_or_two_observation": { "total": 82.11386934995892, "count": 507672, "is_parallel": true, "self": 82.11386934995892 } } } } } } } } } } }, "trainer_advance": { "total": 651.5058636249639, "count": 63460, "self": 3.0051067289683715, "children": { "process_trajectory": { "total": 120.72163768099415, "count": 63460, "self": 120.53827111999396, "children": { "RLTrainer._checkpoint": { "total": 0.18336656100018445, "count": 2, "self": 0.18336656100018445 } } }, "_update_policy": { "total": 527.7791192150014, "count": 446, "self": 293.3733732189967, "children": { "TorchPPOOptimizer.update": { "total": 234.40574599600473, "count": 22824, "self": 234.40574599600473 } } } } } } }, "trainer_threads": { "total": 8.600000001024455e-07, "count": 1, "self": 8.600000001024455e-07 }, "TrainerController._save_models": { "total": 0.07882022000012512, "count": 1, "self": 0.001300997000271309, "children": { "RLTrainer._checkpoint": { "total": 0.07751922299985381, "count": 1, "self": 0.07751922299985381 } } } } } } }