{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7485287189483643, "min": 0.721121072769165, "max": 1.4967479705810547, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 22276.21484375, "min": 21841.314453125, "max": 45405.34765625, "count": 33 }, "Pyramids.Step.mean": { "value": 989881.0, "min": 29952.0, "max": 989881.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989881.0, "min": 29952.0, "max": 989881.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3076791763305664, "min": -0.14929679036140442, "max": 0.3076791763305664, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 79.68890380859375, "min": -35.83123016357422, "max": 79.68890380859375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.04367156699299812, "min": 0.001532378955744207, "max": 0.21783900260925293, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 11.310935974121094, "min": 0.3938213884830475, "max": 52.2813606262207, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06653811537867618, "min": 0.06440809699767638, "max": 0.07328215335152259, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9980717306801428, "min": 0.5051329211509538, "max": 1.0446833896955163, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013864424171171976, "min": 0.0002718750866058465, "max": 0.013864424171171976, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20796636256757964, "min": 0.003323252776208009, "max": 0.20796636256757964, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5201374933199995e-06, "min": 7.5201374933199995e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011280206239979999, "min": 0.00011280206239979999, "max": 0.0030208088930638003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250667999999999, "min": 0.10250667999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376001999999998, "min": 1.3691136000000002, "max": 2.3069362, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000260417332, "min": 0.000260417332, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00390625998, "min": 0.00390625998, "max": 0.10072292637999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006933304015547037, "min": 0.006933304015547037, "max": 0.34265878796577454, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.103999562561512, "min": 0.103999562561512, "max": 2.398611545562744, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 544.0188679245283, "min": 536.6481481481482, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28833.0, "min": 15984.0, "max": 32367.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.267230158706881, "min": -1.0000000521540642, "max": 1.267230158706881, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 67.16319841146469, "min": -32.000001668930054, "max": 67.16319841146469, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.267230158706881, "min": -1.0000000521540642, "max": 1.267230158706881, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 67.16319841146469, "min": -32.000001668930054, "max": 67.16319841146469, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0391788089698409, "min": 0.0391788089698409, "max": 6.95666787866503, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.0764768754015677, "min": 2.0764768754015677, "max": 111.30668605864048, "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": "1718966191", "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/PyramidsRND2.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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718968278" }, "total": 2086.837163489, "count": 1, "self": 0.4942181289998189, "children": { "run_training.setup": { "total": 0.05836002699999199, "count": 1, "self": 0.05836002699999199 }, "TrainerController.start_learning": { "total": 2086.284585333, "count": 1, "self": 1.3563512580476527, "children": { "TrainerController._reset_env": { "total": 2.9884611589999963, "count": 1, "self": 2.9884611589999963 }, "TrainerController.advance": { "total": 2081.8538012199524, "count": 63299, "self": 1.4276900359718638, "children": { "env_step": { "total": 1448.9236645259805, "count": 63299, "self": 1312.7030731379984, "children": { "SubprocessEnvManager._take_step": { "total": 135.39099999900333, "count": 63299, "self": 4.741975187054322, "children": { "TorchPolicy.evaluate": { "total": 130.649024811949, "count": 62555, "self": 130.649024811949 } } }, "workers": { "total": 0.8295913889786561, "count": 63299, "self": 0.0, "children": { "worker_root": { "total": 2081.449556112959, "count": 63299, "is_parallel": true, "self": 892.1336691739725, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005625964999978805, "count": 1, "is_parallel": true, "self": 0.004029850999984319, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015961139999944862, "count": 8, "is_parallel": true, "self": 0.0015961139999944862 } } }, "UnityEnvironment.step": { "total": 0.04793931099999327, "count": 1, "is_parallel": true, "self": 0.000642024000001129, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005080750000274747, "count": 1, "is_parallel": true, "self": 0.0005080750000274747 }, "communicator.exchange": { "total": 0.04498520599997846, "count": 1, "is_parallel": true, "self": 0.04498520599997846 }, "steps_from_proto": { "total": 0.0018040059999862024, "count": 1, "is_parallel": true, "self": 0.00041200199996183073, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013920040000243716, "count": 8, "is_parallel": true, "self": 0.0013920040000243716 } } } } } } }, "UnityEnvironment.step": { "total": 1189.3158869389863, "count": 63298, "is_parallel": true, "self": 33.59821243096371, "children": { "UnityEnvironment._generate_step_input": { "total": 23.832356061981955, "count": 63298, "is_parallel": true, "self": 23.832356061981955 }, "communicator.exchange": { "total": 1033.558183121027, "count": 63298, "is_parallel": true, "self": 1033.558183121027 }, "steps_from_proto": { "total": 98.32713532501367, "count": 63298, "is_parallel": true, "self": 19.953264442975467, "children": { "_process_rank_one_or_two_observation": { "total": 78.3738708820382, "count": 506384, "is_parallel": true, "self": 78.3738708820382 } } } } } } } } } } }, "trainer_advance": { "total": 631.5024466580002, "count": 63299, "self": 2.4144224759598956, "children": { "process_trajectory": { "total": 127.85393436603846, "count": 63299, "self": 127.50993596603877, "children": { "RLTrainer._checkpoint": { "total": 0.3439983999996912, "count": 2, "self": 0.3439983999996912 } } }, "_update_policy": { "total": 501.2340898160018, "count": 432, "self": 295.7051645440182, "children": { "TorchPPOOptimizer.update": { "total": 205.5289252719836, "count": 22821, "self": 205.5289252719836 } } } } } } }, "trainer_threads": { "total": 1.300999883824261e-06, "count": 1, "self": 1.300999883824261e-06 }, "TrainerController._save_models": { "total": 0.08597039500000392, "count": 1, "self": 0.0013751229998888448, "children": { "RLTrainer._checkpoint": { "total": 0.08459527200011507, "count": 1, "self": 0.08459527200011507 } } } } } } }