{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2797270715236664, "min": 0.2797270715236664, "max": 1.4494603872299194, "count": 51 }, "Pyramids.Policy.Entropy.sum": { "value": 8476.849609375, "min": 8476.849609375, "max": 43970.83203125, "count": 51 }, "Pyramids.Step.mean": { "value": 1529991.0, "min": 29952.0, "max": 1529991.0, "count": 51 }, "Pyramids.Step.sum": { "value": 1529991.0, "min": 29952.0, "max": 1529991.0, "count": 51 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5398198962211609, "min": -0.10549866408109665, "max": 0.6009782552719116, "count": 51 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 147.91064453125, "min": -25.42517852783203, "max": 166.47097778320312, "count": 51 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.008302798494696617, "min": -0.010379468090832233, "max": 0.32014110684394836, "count": 51 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.2749667167663574, "min": -2.8647332191467285, "max": 77.15400695800781, "count": 51 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07263698270253371, "min": 0.06581168592120298, "max": 0.07594973567711986, "count": 51 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.016917757835472, "min": 0.4935376666181509, "max": 1.0818804220907623, "count": 51 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01202843454839673, "min": 0.0006601675238454783, "max": 0.014907389456446669, "count": 51 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1683980836775542, "min": 0.00792201028614574, "max": 0.20990820526397633, "count": 51 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00014845887908515238, "min": 0.00014845887908515238, "max": 0.00029838354339596195, "count": 51 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0020784243071921334, "min": 0.0020784243071921334, "max": 0.003927843190718967, "count": 51 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14948627619047622, "min": 0.14948627619047622, "max": 0.19946118095238097, "count": 51 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.092807866666667, "min": 1.3962282666666668, "max": 2.7092810333333333, "count": 51 }, "Pyramids.Policy.Beta.mean": { "value": 0.00495367899142857, "min": 0.00495367899142857, "max": 0.009946171977142856, "count": 51 }, "Pyramids.Policy.Beta.sum": { "value": 0.06935150587999998, "min": 0.06935150587999998, "max": 0.13093717523, "count": 51 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006247273180633783, "min": 0.006247273180633783, "max": 0.4162982106208801, "count": 51 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08746182173490524, "min": 0.08746182173490524, "max": 2.9140875339508057, "count": 51 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 372.5609756097561, "min": 332.6, "max": 999.0, "count": 51 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30550.0, "min": 15984.0, "max": 33950.0, "count": 51 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5294394857353635, "min": -1.0000000521540642, "max": 1.6004578200090362, "count": 51 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 123.88459834456444, "min": -29.87800160050392, "max": 146.5601980611682, "count": 51 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5294394857353635, "min": -1.0000000521540642, "max": 1.6004578200090362, "count": 51 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 123.88459834456444, "min": -29.87800160050392, "max": 146.5601980611682, "count": 51 }, "Pyramids.Policy.RndReward.mean": { "value": 0.024554764987386325, "min": 0.024554764987386325, "max": 7.6601913664489985, "count": 51 }, "Pyramids.Policy.RndReward.sum": { "value": 1.9889359639782924, "min": 1.978144668362802, "max": 122.56306186318398, "count": 51 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 51 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 51 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1724471923", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724476963" }, "total": 5040.241456817, "count": 1, "self": 0.48358017999908043, "children": { "run_training.setup": { "total": 0.07504346499990788, "count": 1, "self": 0.07504346499990788 }, "TrainerController.start_learning": { "total": 5039.682833172001, "count": 1, "self": 3.5302959500922952, "children": { "TrainerController._reset_env": { "total": 3.3901487450002605, "count": 1, "self": 3.3901487450002605 }, "TrainerController.advance": { "total": 5032.6101953259085, "count": 98793, "self": 3.9608414108543, "children": { "env_step": { "total": 3403.325599734051, "count": 98793, "self": 3151.3776006142475, "children": { "SubprocessEnvManager._take_step": { "total": 249.67941184999745, "count": 98793, "self": 11.0534170220958, "children": { "TorchPolicy.evaluate": { "total": 238.62599482790165, "count": 96710, "self": 238.62599482790165 } } }, "workers": { "total": 2.2685872698061758, "count": 98792, "self": 0.0, "children": { "worker_root": { "total": 5028.501087116012, "count": 98792, "is_parallel": true, "self": 2166.5202629661235, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0034656790003282367, "count": 1, "is_parallel": true, "self": 0.0011825940000562696, "children": { "_process_rank_one_or_two_observation": { "total": 0.002283085000271967, "count": 8, "is_parallel": true, "self": 0.002283085000271967 } } }, "UnityEnvironment.step": { "total": 0.08306048299982649, "count": 1, "is_parallel": true, "self": 0.0007720589997006755, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005785889998151106, "count": 1, "is_parallel": true, "self": 0.0005785889998151106 }, "communicator.exchange": { "total": 0.07980466400022124, "count": 1, "is_parallel": true, "self": 0.07980466400022124 }, "steps_from_proto": { "total": 0.0019051710000894673, "count": 1, "is_parallel": true, "self": 0.00042546499980744557, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014797060002820217, "count": 8, "is_parallel": true, "self": 0.0014797060002820217 } } } } } } }, "UnityEnvironment.step": { "total": 2861.9808241498886, "count": 98791, "is_parallel": true, "self": 76.87792465067469, "children": { "UnityEnvironment._generate_step_input": { "total": 47.14168820803934, "count": 98791, "is_parallel": true, "self": 47.14168820803934 }, "communicator.exchange": { "total": 2534.8883740401966, "count": 98791, "is_parallel": true, "self": 2534.8883740401966 }, "steps_from_proto": { "total": 203.07283725097795, "count": 98791, "is_parallel": true, "self": 44.120990863800216, "children": { "_process_rank_one_or_two_observation": { "total": 158.95184638717774, "count": 790328, "is_parallel": true, "self": 158.95184638717774 } } } } } } } } } } }, "trainer_advance": { "total": 1625.3237541810036, "count": 98792, "self": 7.321892404920618, "children": { "process_trajectory": { "total": 253.45929564307653, "count": 98792, "self": 253.1046998920765, "children": { "RLTrainer._checkpoint": { "total": 0.3545957510000335, "count": 3, "self": 0.3545957510000335 } } }, "_update_policy": { "total": 1364.5425661330064, "count": 709, "self": 563.8000871289537, "children": { "TorchPPOOptimizer.update": { "total": 800.7424790040527, "count": 35220, "self": 800.7424790040527 } } } } } } }, "trainer_threads": { "total": 1.7239999579032883e-06, "count": 1, "self": 1.7239999579032883e-06 }, "TrainerController._save_models": { "total": 0.1521914269997069, "count": 1, "self": 0.0028344880001895945, "children": { "RLTrainer._checkpoint": { "total": 0.1493569389995173, "count": 1, "self": 0.1493569389995173 } } } } } } }