{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3023781478404999, "min": 0.3023781478404999, "max": 1.3851267099380493, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9047.154296875, "min": 9047.154296875, "max": 42019.203125, "count": 33 }, "Pyramids.Step.mean": { "value": 989888.0, "min": 29873.0, "max": 989888.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989888.0, "min": 29873.0, "max": 989888.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3720914125442505, "min": -0.09277643263339996, "max": 0.3720914125442505, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 97.11585998535156, "min": -22.359119415283203, "max": 97.11585998535156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.43772897124290466, "min": -0.43772897124290466, "max": 0.33005502820014954, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -114.24726104736328, "min": -114.24726104736328, "max": 79.54325866699219, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06873782694714868, "min": 0.06451474706382396, "max": 0.07308701650019313, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0310674042072303, "min": 0.5116091155013519, "max": 1.0862417079430695, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.027784618391888213, "min": 0.0009425128522200676, "max": 0.044604256470587904, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.4167692758783232, "min": 0.011310154226640811, "max": 0.6244595905882306, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.447137517653333e-06, "min": 7.447137517653333e-06, "max": 0.0002952363015879, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001117070627648, "min": 0.0001117070627648, "max": 0.003634545488484899, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248234666666668, "min": 0.10248234666666668, "max": 0.1984121, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5372352000000002, "min": 1.3888847, "max": 2.6115151, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025798643200000004, "min": 0.00025798643200000004, "max": 0.009841368789999999, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038697964800000003, "min": 0.0038697964800000003, "max": 0.12117035848999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011309059336781502, "min": 0.011277731508016586, "max": 0.5924831032752991, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16963589191436768, "min": 0.16314435005187988, "max": 4.147381782531738, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 493.0769230769231, "min": 459.3968253968254, "max": 996.1, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32050.0, "min": 16544.0, "max": 33496.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1991599783301354, "min": -0.93032005255421, "max": 1.4135936210079798, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 77.9453985914588, "min": -28.575801625847816, "max": 89.05639812350273, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1991599783301354, "min": -0.93032005255421, "max": 1.4135936210079798, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 77.9453985914588, "min": -28.575801625847816, "max": 89.05639812350273, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05725687068143788, "min": 0.05432561445466952, "max": 11.161639002316138, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.721696594293462, "min": 3.4639352806843817, "max": 189.74786303937435, "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": "1679878663", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679880906" }, "total": 2242.628757988, "count": 1, "self": 0.5904768440004773, "children": { "run_training.setup": { "total": 0.1733352730000206, "count": 1, "self": 0.1733352730000206 }, "TrainerController.start_learning": { "total": 2241.8649458709997, "count": 1, "self": 1.8260159289520743, "children": { "TrainerController._reset_env": { "total": 9.386494696, "count": 1, "self": 9.386494696 }, "TrainerController.advance": { "total": 2230.5558218750475, "count": 63570, "self": 1.9545012550024694, "children": { "env_step": { "total": 1575.3374323760445, "count": 63570, "self": 1445.327589238058, "children": { "SubprocessEnvManager._take_step": { "total": 128.90409589900486, "count": 63570, "self": 5.530283208047365, "children": { "TorchPolicy.evaluate": { "total": 123.3738126909575, "count": 62561, "self": 123.3738126909575 } } }, "workers": { "total": 1.105747238981678, "count": 63570, "self": 0.0, "children": { "worker_root": { "total": 2236.1136092039274, "count": 63570, "is_parallel": true, "self": 926.9765567779423, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005914359999962926, "count": 1, "is_parallel": true, "self": 0.0039002400000072157, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020141199999557102, "count": 8, "is_parallel": true, "self": 0.0020141199999557102 } } }, "UnityEnvironment.step": { "total": 0.05079742499998474, "count": 1, "is_parallel": true, "self": 0.0005627999999546773, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005408300000340205, "count": 1, "is_parallel": true, "self": 0.0005408300000340205 }, "communicator.exchange": { "total": 0.0478714489999561, "count": 1, "is_parallel": true, "self": 0.0478714489999561 }, "steps_from_proto": { "total": 0.0018223460000399427, "count": 1, "is_parallel": true, "self": 0.0004176430000484288, "children": { "_process_rank_one_or_two_observation": { "total": 0.001404702999991514, "count": 8, "is_parallel": true, "self": 0.001404702999991514 } } } } } } }, "UnityEnvironment.step": { "total": 1309.137052425985, "count": 63569, "is_parallel": true, "self": 34.42142797188035, "children": { "UnityEnvironment._generate_step_input": { "total": 25.62193662304412, "count": 63569, "is_parallel": true, "self": 25.62193662304412 }, "communicator.exchange": { "total": 1145.0924451590486, "count": 63569, "is_parallel": true, "self": 1145.0924451590486 }, "steps_from_proto": { "total": 104.00124267201193, "count": 63569, "is_parallel": true, "self": 23.37512846807755, "children": { "_process_rank_one_or_two_observation": { "total": 80.62611420393438, "count": 508552, "is_parallel": true, "self": 80.62611420393438 } } } } } } } } } } }, "trainer_advance": { "total": 653.2638882440007, "count": 63570, "self": 3.3727580900273324, "children": { "process_trajectory": { "total": 131.09013973797465, "count": 63570, "self": 130.87539030797444, "children": { "RLTrainer._checkpoint": { "total": 0.21474943000021085, "count": 2, "self": 0.21474943000021085 } } }, "_update_policy": { "total": 518.8009904159987, "count": 457, "self": 329.9478973829904, "children": { "TorchPPOOptimizer.update": { "total": 188.85309303300835, "count": 22803, "self": 188.85309303300835 } } } } } } }, "trainer_threads": { "total": 1.0650001058820635e-06, "count": 1, "self": 1.0650001058820635e-06 }, "TrainerController._save_models": { "total": 0.09661230599976989, "count": 1, "self": 0.0014541739997184777, "children": { "RLTrainer._checkpoint": { "total": 0.09515813200005141, "count": 1, "self": 0.09515813200005141 } } } } } } }