{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.25048187375068665, "min": 0.25048187375068665, "max": 1.4666286706924438, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 7378.1943359375, "min": 7378.1943359375, "max": 44491.6484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6338657736778259, "min": -0.10115662217140198, "max": 0.6697325706481934, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 178.1162872314453, "min": -24.581058502197266, "max": 192.8829803466797, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.045981328934431076, "min": 0.02093038707971573, "max": 0.31808170676231384, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.920753479003906, "min": 5.923299312591553, "max": 76.6576919555664, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06853668947033362, "min": 0.06483580723072678, "max": 0.07256610408198158, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9595136525846707, "min": 0.47963413942120864, "max": 1.0682748514296048, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015163678697717842, "min": 0.0020859294454486756, "max": 0.01805130425158755, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21229150176804978, "min": 0.020602714817609245, "max": 0.2527182595222257, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.746740274928571e-06, "min": 7.746740274928571e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.000108454363849, "min": 0.000108454363849, "max": 0.0033842993719002995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10258221428571428, "min": 0.10258221428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.436151, "min": 1.3886848, "max": 2.6174296999999997, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026796320714285725, "min": 0.00026796320714285725, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037514849000000014, "min": 0.0037514849000000014, "max": 0.11283716003, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016973374411463737, "min": 0.016973374411463737, "max": 0.44356223940849304, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23762723803520203, "min": 0.23762723803520203, "max": 3.104935646057129, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 288.52941176470586, "min": 275.7232142857143, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29430.0, "min": 15984.0, "max": 33672.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.672243126832387, "min": -1.0000000521540642, "max": 1.7020660212158032, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 170.56879893690348, "min": -30.711601726710796, "max": 187.1173982322216, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.672243126832387, "min": -1.0000000521540642, "max": 1.7020660212158032, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 170.56879893690348, "min": -30.711601726710796, "max": 187.1173982322216, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.050673578508590875, "min": 0.04931360975271153, "max": 8.190888339653611, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.1687050078762695, "min": 5.1687050078762695, "max": 131.05421343445778, "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": "1706798286", "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 1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706800766" }, "total": 2480.15269914, "count": 1, "self": 1.1649721750000026, "children": { "run_training.setup": { "total": 0.047923879000336456, "count": 1, "self": 0.047923879000336456 }, "TrainerController.start_learning": { "total": 2478.9398030859998, "count": 1, "self": 1.4981742180330002, "children": { "TrainerController._reset_env": { "total": 2.3743414549999216, "count": 1, "self": 2.3743414549999216 }, "TrainerController.advance": { "total": 2474.919688922968, "count": 64339, "self": 1.6219061519832394, "children": { "env_step": { "total": 1825.219570098082, "count": 64339, "self": 1685.3922725169887, "children": { "SubprocessEnvManager._take_step": { "total": 138.90319245102364, "count": 64339, "self": 5.111646914027915, "children": { "TorchPolicy.evaluate": { "total": 133.79154553699573, "count": 62553, "self": 133.79154553699573 } } }, "workers": { "total": 0.9241051300696199, "count": 64339, "self": 0.0, "children": { "worker_root": { "total": 2473.0799398869985, "count": 64339, "is_parallel": true, "self": 916.8079562979242, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021232180001788947, "count": 1, "is_parallel": true, "self": 0.0006955439994271728, "children": { "_process_rank_one_or_two_observation": { "total": 0.001427674000751722, "count": 8, "is_parallel": true, "self": 0.001427674000751722 } } }, "UnityEnvironment.step": { "total": 0.05868231599970386, "count": 1, "is_parallel": true, "self": 0.000657816999591887, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008271670003523468, "count": 1, "is_parallel": true, "self": 0.0008271670003523468 }, "communicator.exchange": { "total": 0.05555072900006053, "count": 1, "is_parallel": true, "self": 0.05555072900006053 }, "steps_from_proto": { "total": 0.0016466029996990983, "count": 1, "is_parallel": true, "self": 0.00036374700039232266, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012828559993067756, "count": 8, "is_parallel": true, "self": 0.0012828559993067756 } } } } } } }, "UnityEnvironment.step": { "total": 1556.2719835890744, "count": 64338, "is_parallel": true, "self": 36.94794790611559, "children": { "UnityEnvironment._generate_step_input": { "total": 26.851170452899623, "count": 64338, "is_parallel": true, "self": 26.851170452899623 }, "communicator.exchange": { "total": 1383.2454405859808, "count": 64338, "is_parallel": true, "self": 1383.2454405859808 }, "steps_from_proto": { "total": 109.22742464407838, "count": 64338, "is_parallel": true, "self": 22.579166110927417, "children": { "_process_rank_one_or_two_observation": { "total": 86.64825853315097, "count": 514704, "is_parallel": true, "self": 86.64825853315097 } } } } } } } } } } }, "trainer_advance": { "total": 648.0782126729027, "count": 64339, "self": 2.8697625428294486, "children": { "process_trajectory": { "total": 135.3643829320731, "count": 64339, "self": 135.11329923407266, "children": { "RLTrainer._checkpoint": { "total": 0.25108369800045693, "count": 2, "self": 0.25108369800045693 } } }, "_update_policy": { "total": 509.8440671980002, "count": 451, "self": 300.5464728280317, "children": { "TorchPPOOptimizer.update": { "total": 209.29759436996846, "count": 22746, "self": 209.29759436996846 } } } } } } }, "trainer_threads": { "total": 1.3319995559868403e-06, "count": 1, "self": 1.3319995559868403e-06 }, "TrainerController._save_models": { "total": 0.14759715799937112, "count": 1, "self": 0.0021744359992226236, "children": { "RLTrainer._checkpoint": { "total": 0.1454227220001485, "count": 1, "self": 0.1454227220001485 } } } } } } }