{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3104543387889862, "min": 0.301523357629776, "max": 1.4333807229995728, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9403.041015625, "min": 8987.80859375, "max": 43483.0390625, "count": 33 }, "Pyramids.Step.mean": { "value": 989924.0, "min": 29952.0, "max": 989924.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989924.0, "min": 29952.0, "max": 989924.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6272243857383728, "min": -0.10512984544038773, "max": 0.6272243857383728, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 180.01339721679688, "min": -25.336292266845703, "max": 180.01339721679688, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0612083338201046, "min": -0.23100244998931885, "max": 0.3667655885219574, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -17.566791534423828, "min": -57.98161315917969, "max": 88.02374267578125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06705715397921658, "min": 0.0655090932945112, "max": 0.07335920189115432, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9388001557090321, "min": 0.5115256524270456, "max": 1.0510968907888039, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016802692891880206, "min": 0.00021406722860660787, "max": 0.02426672102267346, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23523770048632286, "min": 0.0023547395146726866, "max": 0.3397340943174284, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.474061794392859e-06, "min": 7.474061794392859e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010463686512150002, "min": 0.00010463686512150002, "max": 0.0032538356153881997, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249132142857145, "min": 0.10249132142857145, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348785000000004, "min": 1.3691136000000002, "max": 2.4432301, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002588830107142858, "min": 0.0002588830107142858, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036243621500000015, "min": 0.0036243621500000015, "max": 0.10848271881999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012952017597854137, "min": 0.01275254599750042, "max": 0.5803607106208801, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18132825195789337, "min": 0.17853564023971558, "max": 4.062524795532227, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 308.26666666666665, "min": 291.11340206185565, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32368.0, "min": 15984.0, "max": 34457.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6536228360164733, "min": -1.0000000521540642, "max": 1.6883374832880993, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 173.6303977817297, "min": -32.000001668930054, "max": 173.6303977817297, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6536228360164733, "min": -1.0000000521540642, "max": 1.6883374832880993, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 173.6303977817297, "min": -32.000001668930054, "max": 173.6303977817297, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04163343059176224, "min": 0.04084722981254648, "max": 11.731236949563026, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.3715102121350355, "min": 3.6925790069362847, "max": 187.69979119300842, "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": "1731955699", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1731957995" }, "total": 2295.8781507229996, "count": 1, "self": 0.48686025499955576, "children": { "run_training.setup": { "total": 0.054804972000056296, "count": 1, "self": 0.054804972000056296 }, "TrainerController.start_learning": { "total": 2295.336485496, "count": 1, "self": 1.3301299250192642, "children": { "TrainerController._reset_env": { "total": 2.6530231340000228, "count": 1, "self": 2.6530231340000228 }, "TrainerController.advance": { "total": 2291.2713852259803, "count": 63966, "self": 1.386771362997024, "children": { "env_step": { "total": 1608.6415012679804, "count": 63966, "self": 1458.9080388689433, "children": { "SubprocessEnvManager._take_step": { "total": 148.94021840401547, "count": 63966, "self": 4.5533654371083685, "children": { "TorchPolicy.evaluate": { "total": 144.3868529669071, "count": 62558, "self": 144.3868529669071 } } }, "workers": { "total": 0.7932439950216121, "count": 63966, "self": 0.0, "children": { "worker_root": { "total": 2290.383351122994, "count": 63966, "is_parallel": true, "self": 947.6562816419944, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002005866000217793, "count": 1, "is_parallel": true, "self": 0.0006275050000112969, "children": { "_process_rank_one_or_two_observation": { "total": 0.001378361000206496, "count": 8, "is_parallel": true, "self": 0.001378361000206496 } } }, "UnityEnvironment.step": { "total": 0.09128803599992352, "count": 1, "is_parallel": true, "self": 0.003751399999828209, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000497490000043399, "count": 1, "is_parallel": true, "self": 0.000497490000043399 }, "communicator.exchange": { "total": 0.0851408480000373, "count": 1, "is_parallel": true, "self": 0.0851408480000373 }, "steps_from_proto": { "total": 0.00189829800001462, "count": 1, "is_parallel": true, "self": 0.0005114250000133325, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013868730000012874, "count": 8, "is_parallel": true, "self": 0.0013868730000012874 } } } } } } }, "UnityEnvironment.step": { "total": 1342.7270694809997, "count": 63965, "is_parallel": true, "self": 32.85936809499958, "children": { "UnityEnvironment._generate_step_input": { "total": 23.510800177009287, "count": 63965, "is_parallel": true, "self": 23.510800177009287 }, "communicator.exchange": { "total": 1188.3946216590282, "count": 63965, "is_parallel": true, "self": 1188.3946216590282 }, "steps_from_proto": { "total": 97.96227954996266, "count": 63965, "is_parallel": true, "self": 20.21323262596775, "children": { "_process_rank_one_or_two_observation": { "total": 77.74904692399491, "count": 511720, "is_parallel": true, "self": 77.74904692399491 } } } } } } } } } } }, "trainer_advance": { "total": 681.2431125950027, "count": 63966, "self": 2.5189358169845946, "children": { "process_trajectory": { "total": 131.94726472101593, "count": 63966, "self": 131.75261288801585, "children": { "RLTrainer._checkpoint": { "total": 0.19465183300007993, "count": 2, "self": 0.19465183300007993 } } }, "_update_policy": { "total": 546.7769120570022, "count": 442, "self": 307.8569950800061, "children": { "TorchPPOOptimizer.update": { "total": 238.9199169769961, "count": 22842, "self": 238.9199169769961 } } } } } } }, "trainer_threads": { "total": 9.34000127017498e-07, "count": 1, "self": 9.34000127017498e-07 }, "TrainerController._save_models": { "total": 0.08194627700004276, "count": 1, "self": 0.00142687500010652, "children": { "RLTrainer._checkpoint": { "total": 0.08051940199993624, "count": 1, "self": 0.08051940199993624 } } } } } } }