{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.46350395679473877, "min": 0.4490824341773987, "max": 1.3850147724151611, "count": 40 }, "Pyramids.Policy.Entropy.sum": { "value": 13838.3740234375, "min": 13458.1025390625, "max": 42015.80859375, "count": 40 }, "Pyramids.Step.mean": { "value": 1199927.0, "min": 29952.0, "max": 1199927.0, "count": 40 }, "Pyramids.Step.sum": { "value": 1199927.0, "min": 29952.0, "max": 1199927.0, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4782269597053528, "min": -0.09765279293060303, "max": 0.5801189541816711, "count": 40 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 129.12127685546875, "min": -23.53432273864746, "max": 161.2730712890625, "count": 40 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -3.016075372695923, "min": -3.016075372695923, "max": 0.372019499540329, "count": 40 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -814.34033203125, "min": -814.34033203125, "max": 88.16862487792969, "count": 40 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06568315474470394, "min": 0.06412611973896024, "max": 0.07354925078726622, "count": 40 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9195641664258551, "min": 0.5137745890073576, "max": 1.072930386842927, "count": 40 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.6159976092897649, "min": 0.0006525528170308608, "max": 0.6159976092897649, "count": 40 }, "Pyramids.Losses.ValueLoss.sum": { "value": 8.623966530056709, "min": 0.007178080987339468, "max": 8.623966530056709, "count": 40 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.6101166538035735e-06, "min": 3.6101166538035735e-06, "max": 0.0002959588584899048, "count": 40 }, "Pyramids.Policy.LearningRate.sum": { "value": 5.0541633153250027e-05, "min": 5.0541633153250027e-05, "max": 0.0036231044422985826, "count": 40 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10120333928571427, "min": 0.10120333928571427, "max": 0.1986529523809524, "count": 40 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.41684675, "min": 1.3905706666666668, "max": 2.6077014166666665, "count": 40 }, "Pyramids.Policy.Beta.mean": { "value": 0.00013021359464285726, "min": 0.00013021359464285726, "max": 0.00986542994285714, "count": 40 }, "Pyramids.Policy.Beta.sum": { "value": 0.0018229903250000018, "min": 0.0018229903250000018, "max": 0.12078937152500001, "count": 40 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007832879200577736, "min": 0.007746610324829817, "max": 0.4026288092136383, "count": 40 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.109660305082798, "min": 0.10845254361629486, "max": 2.818401575088501, "count": 40 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 384.1818181818182, "min": 330.4166666666667, "max": 999.0, "count": 40 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29582.0, "min": 15984.0, "max": 32988.0, "count": 40 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4858934895752312, "min": -1.0000000521540642, "max": 1.621945216453501, "count": 40 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 114.4137986972928, "min": -30.995801597833633, "max": 148.12599824368954, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4858934895752312, "min": -1.0000000521540642, "max": 1.621945216453501, "count": 40 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 114.4137986972928, "min": -30.995801597833633, "max": 148.12599824368954, "count": 40 }, "Pyramids.Policy.RndReward.mean": { "value": 0.031150284076652674, "min": 0.02790289833861333, "max": 7.8628083961084485, "count": 40 }, "Pyramids.Policy.RndReward.sum": { "value": 2.398571873902256, "min": 2.398571873902256, "max": 125.80493433773518, "count": 40 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1711054534", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1711057154" }, "total": 2620.1119485010004, "count": 1, "self": 0.5381635220001044, "children": { "run_training.setup": { "total": 0.053618530999983705, "count": 1, "self": 0.053618530999983705 }, "TrainerController.start_learning": { "total": 2619.520166448, "count": 1, "self": 1.600142981937097, "children": { "TrainerController._reset_env": { "total": 3.1197774929999014, "count": 1, "self": 3.1197774929999014 }, "TrainerController.advance": { "total": 2614.7069697180627, "count": 76558, "self": 1.7083653741538, "children": { "env_step": { "total": 1852.604231632902, "count": 76558, "self": 1697.7971804707706, "children": { "SubprocessEnvManager._take_step": { "total": 153.82967421206126, "count": 76558, "self": 5.660733128016091, "children": { "TorchPolicy.evaluate": { "total": 148.16894108404517, "count": 75044, "self": 148.16894108404517 } } }, "workers": { "total": 0.9773769500700382, "count": 76558, "self": 0.0, "children": { "worker_root": { "total": 2613.3849470400964, "count": 76558, "is_parallel": true, "self": 1060.6016531831262, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005639790000032008, "count": 1, "is_parallel": true, "self": 0.003922510000393231, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017172799996387766, "count": 8, "is_parallel": true, "self": 0.0017172799996387766 } } }, "UnityEnvironment.step": { "total": 0.04842754099990998, "count": 1, "is_parallel": true, "self": 0.0006331709998903534, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004610660000707867, "count": 1, "is_parallel": true, "self": 0.0004610660000707867 }, "communicator.exchange": { "total": 0.04562233899991952, "count": 1, "is_parallel": true, "self": 0.04562233899991952 }, "steps_from_proto": { "total": 0.0017109650000293186, "count": 1, "is_parallel": true, "self": 0.0003800710001087282, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013308939999205904, "count": 8, "is_parallel": true, "self": 0.0013308939999205904 } } } } } } }, "UnityEnvironment.step": { "total": 1552.7832938569702, "count": 76557, "is_parallel": true, "self": 41.633477742795776, "children": { "UnityEnvironment._generate_step_input": { "total": 28.359959324095826, "count": 76557, "is_parallel": true, "self": 28.359959324095826 }, "communicator.exchange": { "total": 1361.4395047530493, "count": 76557, "is_parallel": true, "self": 1361.4395047530493 }, "steps_from_proto": { "total": 121.35035203702932, "count": 76557, "is_parallel": true, "self": 24.465708466855403, "children": { "_process_rank_one_or_two_observation": { "total": 96.88464357017392, "count": 612456, "is_parallel": true, "self": 96.88464357017392 } } } } } } } } } } }, "trainer_advance": { "total": 760.394372711007, "count": 76558, "self": 3.241308591989764, "children": { "process_trajectory": { "total": 154.97048631001599, "count": 76558, "self": 154.68984164701578, "children": { "RLTrainer._checkpoint": { "total": 0.28064466300020285, "count": 2, "self": 0.28064466300020285 } } }, "_update_policy": { "total": 602.1825778090013, "count": 543, "self": 353.93209706503376, "children": { "TorchPPOOptimizer.update": { "total": 248.2504807439675, "count": 27384, "self": 248.2504807439675 } } } } } } }, "trainer_threads": { "total": 8.510000952810515e-07, "count": 1, "self": 8.510000952810515e-07 }, "TrainerController._save_models": { "total": 0.09327540399999634, "count": 1, "self": 0.0014869689998704416, "children": { "RLTrainer._checkpoint": { "total": 0.0917884350001259, "count": 1, "self": 0.0917884350001259 } } } } } } }