{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2737155854701996, "min": 0.2737155854701996, "max": 1.4636592864990234, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8128.2578125, "min": 8128.2578125, "max": 44401.56640625, "count": 33 }, "Pyramids.Step.mean": { "value": 989901.0, "min": 29952.0, "max": 989901.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989901.0, "min": 29952.0, "max": 989901.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5711452960968018, "min": -0.08777591586112976, "max": 0.6317324042320251, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 159.92068481445312, "min": -21.153995513916016, "max": 180.6754608154297, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02830958366394043, "min": -0.026873625814914703, "max": 0.5821145176887512, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.92668342590332, "min": -6.825901031494141, "max": 137.9611358642578, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07000973117135886, "min": 0.0641350160225818, "max": 0.07408802489324187, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9801362363990241, "min": 0.4999073677463457, "max": 1.0664408130687664, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016412346961650264, "min": 0.00028157564408214135, "max": 0.017568348714294624, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22977285746310372, "min": 0.0019710295085749894, "max": 0.2550734743175174, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.258404723421429e-06, "min": 7.258404723421429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001016176661279, "min": 0.0001016176661279, "max": 0.0032175469274845, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10241943571428573, "min": 0.10241943571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338721000000003, "min": 1.327104, "max": 2.5725155000000006, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025170162785714297, "min": 0.00025170162785714297, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035238227900000014, "min": 0.0035238227900000014, "max": 0.10729429845, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01111177634447813, "min": 0.01111177634447813, "max": 0.36652323603630066, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.15556487441062927, "min": 0.15556487441062927, "max": 2.5656626224517822, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 323.70103092783506, "min": 308.12371134020617, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31399.0, "min": 15984.0, "max": 32415.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.614426787981053, "min": -1.0000000521540642, "max": 1.6738291482130687, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 156.59939843416214, "min": -32.000001668930054, "max": 160.6875982284546, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.614426787981053, "min": -1.0000000521540642, "max": 1.6738291482130687, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 156.59939843416214, "min": -32.000001668930054, "max": 160.6875982284546, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03706810462248653, "min": 0.03706810462248653, "max": 7.271036705002189, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.5956061483811936, "min": 3.294545262819156, "max": 116.33658728003502, "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": "1751144409", "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", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1751146638" }, "total": 2229.4143894649997, "count": 1, "self": 0.47602322199963965, "children": { "run_training.setup": { "total": 0.020007694000014453, "count": 1, "self": 0.020007694000014453 }, "TrainerController.start_learning": { "total": 2228.918358549, "count": 1, "self": 1.2853784940202786, "children": { "TrainerController._reset_env": { "total": 2.2730405299998893, "count": 1, "self": 2.2730405299998893 }, "TrainerController.advance": { "total": 2225.2807002079803, "count": 63948, "self": 1.362135683867109, "children": { "env_step": { "total": 1564.0361288090637, "count": 63948, "self": 1417.730686335073, "children": { "SubprocessEnvManager._take_step": { "total": 145.51534128001504, "count": 63948, "self": 4.537451229932458, "children": { "TorchPolicy.evaluate": { "total": 140.97789005008258, "count": 62538, "self": 140.97789005008258 } } }, "workers": { "total": 0.7901011939757154, "count": 63948, "self": 0.0, "children": { "worker_root": { "total": 2223.8238351910613, "count": 63948, "is_parallel": true, "self": 917.0646645521256, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017428329999802372, "count": 1, "is_parallel": true, "self": 0.000544438999668273, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011983940003119642, "count": 8, "is_parallel": true, "self": 0.0011983940003119642 } } }, "UnityEnvironment.step": { "total": 0.056696920999911526, "count": 1, "is_parallel": true, "self": 0.0005280889997720806, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046302300006573205, "count": 1, "is_parallel": true, "self": 0.00046302300006573205 }, "communicator.exchange": { "total": 0.054181516000198826, "count": 1, "is_parallel": true, "self": 0.054181516000198826 }, "steps_from_proto": { "total": 0.0015242929998748878, "count": 1, "is_parallel": true, "self": 0.00032026299959397875, "children": { "_process_rank_one_or_two_observation": { "total": 0.001204030000280909, "count": 8, "is_parallel": true, "self": 0.001204030000280909 } } } } } } }, "UnityEnvironment.step": { "total": 1306.7591706389358, "count": 63947, "is_parallel": true, "self": 32.28764648497713, "children": { "UnityEnvironment._generate_step_input": { "total": 23.044011226985504, "count": 63947, "is_parallel": true, "self": 23.044011226985504 }, "communicator.exchange": { "total": 1156.2718901660107, "count": 63947, "is_parallel": true, "self": 1156.2718901660107 }, "steps_from_proto": { "total": 95.15562276096239, "count": 63947, "is_parallel": true, "self": 18.655950168900517, "children": { "_process_rank_one_or_two_observation": { "total": 76.49967259206187, "count": 511576, "is_parallel": true, "self": 76.49967259206187 } } } } } } } } } } }, "trainer_advance": { "total": 659.8824357150495, "count": 63948, "self": 2.5481671930326684, "children": { "process_trajectory": { "total": 126.94658287701031, "count": 63948, "self": 126.75597779000964, "children": { "RLTrainer._checkpoint": { "total": 0.19060508700067658, "count": 2, "self": 0.19060508700067658 } } }, "_update_policy": { "total": 530.3876856450065, "count": 434, "self": 294.2917523529993, "children": { "TorchPPOOptimizer.update": { "total": 236.0959332920072, "count": 22806, "self": 236.0959332920072 } } } } } } }, "trainer_threads": { "total": 8.249999154941179e-07, "count": 1, "self": 8.249999154941179e-07 }, "TrainerController._save_models": { "total": 0.07923849199960387, "count": 1, "self": 0.0013186989999667276, "children": { "RLTrainer._checkpoint": { "total": 0.07791979299963714, "count": 1, "self": 0.07791979299963714 } } } } } } }