{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16783666610717773, "min": 0.15358886122703552, "max": 1.4708518981933594, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5021.6728515625, "min": 4607.666015625, "max": 44619.76171875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999942.0, "min": 29952.0, "max": 2999942.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999942.0, "min": 29952.0, "max": 2999942.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6973609924316406, "min": -0.09299053996801376, "max": 0.8225314021110535, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 203.62940979003906, "min": -22.317729949951172, "max": 245.9368896484375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.001242887694388628, "min": -0.007132279220968485, "max": 0.17455416917800903, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.36292320489883423, "min": -1.9471122026443481, "max": 42.06755447387695, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06905140509932405, "min": 0.06413149599116184, "max": 0.07381289942122878, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0357710764898607, "min": 0.49333935873997775, "max": 1.0835568638947592, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014550859361447186, "min": 0.0002089384176870284, "max": 0.01680049515370552, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2182628904217078, "min": 0.0025072610122443407, "max": 0.239025979739381, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.509612830162214e-06, "min": 1.509612830162214e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.264419245243321e-05, "min": 2.264419245243321e-05, "max": 0.004027476957507733, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050317111111111, "min": 0.10050317111111111, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5075475666666667, "min": 1.3962282666666668, "max": 2.8424922666666665, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.0266793999999736e-05, "min": 6.0266793999999736e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.000904001909999996, "min": 0.000904001909999996, "max": 0.13426497744000002, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005357326008379459, "min": 0.005357326008379459, "max": 0.32975873351097107, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08035989105701447, "min": 0.07502707093954086, "max": 2.3083112239837646, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 252.9145299145299, "min": 214.53521126760563, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29591.0, "min": 15984.0, "max": 33394.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6957863103757558, "min": -1.0000000521540642, "max": 1.7713788573590803, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 198.4069983139634, "min": -29.997601568698883, "max": 251.5357977449894, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6957863103757558, "min": -1.0000000521540642, "max": 1.7713788573590803, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 198.4069983139634, "min": -29.997601568698883, "max": 251.5357977449894, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014116182130051013, "min": 0.012964783143359736, "max": 6.436169371008873, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6515933092159685, "min": 1.5907608448469546, "max": 102.97870993614197, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1711404427", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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": "1711411633" }, "total": 7206.109365287, "count": 1, "self": 0.5396442930014018, "children": { "run_training.setup": { "total": 0.05677559300011126, "count": 1, "self": 0.05677559300011126 }, "TrainerController.start_learning": { "total": 7205.512945400999, "count": 1, "self": 4.2182311641699926, "children": { "TrainerController._reset_env": { "total": 3.1138301180001235, "count": 1, "self": 3.1138301180001235 }, "TrainerController.advance": { "total": 7198.090180509828, "count": 194919, "self": 4.100993252784974, "children": { "env_step": { "total": 5289.2582943980815, "count": 194919, "self": 4902.792998514931, "children": { "SubprocessEnvManager._take_step": { "total": 383.93010127811294, "count": 194919, "self": 13.859834467001292, "children": { "TorchPolicy.evaluate": { "total": 370.07026681111165, "count": 187562, "self": 370.07026681111165 } } }, "workers": { "total": 2.5351946050368497, "count": 194919, "self": 0.0, "children": { "worker_root": { "total": 7189.891571042769, "count": 194919, "is_parallel": true, "self": 2647.453346263933, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006027688999893144, "count": 1, "is_parallel": true, "self": 0.004436073000078977, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015916159998141666, "count": 8, "is_parallel": true, "self": 0.0015916159998141666 } } }, "UnityEnvironment.step": { "total": 0.050876618999836865, "count": 1, "is_parallel": true, "self": 0.0006227249998573825, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004520420000062586, "count": 1, "is_parallel": true, "self": 0.0004520420000062586 }, "communicator.exchange": { "total": 0.0482017659999201, "count": 1, "is_parallel": true, "self": 0.0482017659999201 }, "steps_from_proto": { "total": 0.0016000860000531247, "count": 1, "is_parallel": true, "self": 0.0003400209998289938, "children": { "_process_rank_one_or_two_observation": { "total": 0.001260065000224131, "count": 8, "is_parallel": true, "self": 0.001260065000224131 } } } } } } }, "UnityEnvironment.step": { "total": 4542.438224778836, "count": 194918, "is_parallel": true, "self": 103.9357235068037, "children": { "UnityEnvironment._generate_step_input": { "total": 69.95007993012882, "count": 194918, "is_parallel": true, "self": 69.95007993012882 }, "communicator.exchange": { "total": 4071.1636949659774, "count": 194918, "is_parallel": true, "self": 4071.1636949659774 }, "steps_from_proto": { "total": 297.38872637592567, "count": 194918, "is_parallel": true, "self": 60.05933584511126, "children": { "_process_rank_one_or_two_observation": { "total": 237.3293905308144, "count": 1559344, "is_parallel": true, "self": 237.3293905308144 } } } } } } } } } } }, "trainer_advance": { "total": 1904.730892858962, "count": 194919, "self": 8.983157586103061, "children": { "process_trajectory": { "total": 396.335190450857, "count": 194919, "self": 395.6236039588564, "children": { "RLTrainer._checkpoint": { "total": 0.7115864920006061, "count": 6, "self": 0.7115864920006061 } } }, "_update_policy": { "total": 1499.412544822002, "count": 1398, "self": 875.3016250940218, "children": { "TorchPPOOptimizer.update": { "total": 624.1109197279802, "count": 68379, "self": 624.1109197279802 } } } } } } }, "trainer_threads": { "total": 8.820006769383326e-07, "count": 1, "self": 8.820006769383326e-07 }, "TrainerController._save_models": { "total": 0.09070272700046189, "count": 1, "self": 0.0018354280018684221, "children": { "RLTrainer._checkpoint": { "total": 0.08886729899859347, "count": 1, "self": 0.08886729899859347 } } } } } } }