{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3176240026950836, "min": 0.3176240026950836, "max": 1.4078160524368286, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9625.27734375, "min": 9625.27734375, "max": 42707.5078125, "count": 33 }, "Pyramids.Step.mean": { "value": 989952.0, "min": 29934.0, "max": 989952.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989952.0, "min": 29934.0, "max": 989952.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6264662146568298, "min": -0.07948450744152069, "max": 0.6330125331878662, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 179.16934204101562, "min": -19.155765533447266, "max": 179.16934204101562, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.010167896747589111, "min": -0.03611525148153305, "max": 0.405227929353714, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.9080185890197754, "min": -10.148386001586914, "max": 96.03901672363281, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06750961403633329, "min": 0.06569960350819658, "max": 0.07435372414840578, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0126442105449993, "min": 0.47958796095064893, "max": 1.0785029756370932, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018250664120260017, "min": 0.0008854382073355037, "max": 0.01881936385820643, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2737599618039003, "min": 0.008854382073355037, "max": 0.2737599618039003, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5208174930933344e-06, "min": 7.5208174930933344e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011281226239640002, "min": 0.00011281226239640002, "max": 0.0037603354465548995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250690666666668, "min": 0.10250690666666668, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5376036000000002, "min": 1.3886848, "max": 2.6534451, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026043997600000006, "min": 0.00026043997600000006, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003906599640000001, "min": 0.003906599640000001, "max": 0.12535916548999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009131926111876965, "min": 0.009062698110938072, "max": 0.42660340666770935, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1369788944721222, "min": 0.1268777698278427, "max": 2.9862239360809326, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 274.2, "min": 274.2, "max": 991.8235294117648, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28791.0, "min": 16861.0, "max": 32631.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7257999879973276, "min": -0.9275563033297658, "max": 1.7257999879973276, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 181.2089987397194, "min": -29.681801706552505, "max": 181.2089987397194, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7257999879973276, "min": -0.9275563033297658, "max": 1.7257999879973276, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 181.2089987397194, "min": -29.681801706552505, "max": 181.2089987397194, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02603166069444948, "min": 0.02603166069444948, "max": 9.20870790674406, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7333243729171954, "min": 2.7333243729171954, "max": 156.548034414649, "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": "1692474035", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1692476421" }, "total": 2385.7635191300005, "count": 1, "self": 1.1398265700017873, "children": { "run_training.setup": { "total": 0.039800353999453364, "count": 1, "self": 0.039800353999453364 }, "TrainerController.start_learning": { "total": 2384.5838922059993, "count": 1, "self": 1.43175545304166, "children": { "TrainerController._reset_env": { "total": 4.028379483999743, "count": 1, "self": 4.028379483999743 }, "TrainerController.advance": { "total": 2378.9574415559573, "count": 64200, "self": 1.5593161039860206, "children": { "env_step": { "total": 1696.1974868390162, "count": 64200, "self": 1581.1558944628578, "children": { "SubprocessEnvManager._take_step": { "total": 114.15801947410091, "count": 64200, "self": 4.988137964079215, "children": { "TorchPolicy.evaluate": { "total": 109.1698815100217, "count": 62565, "self": 109.1698815100217 } } }, "workers": { "total": 0.8835729020574945, "count": 64200, "self": 0.0, "children": { "worker_root": { "total": 2378.8353249059937, "count": 64200, "is_parallel": true, "self": 920.0597535019606, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002013928999986092, "count": 1, "is_parallel": true, "self": 0.000578698000026634, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014352309999594581, "count": 8, "is_parallel": true, "self": 0.0014352309999594581 } } }, "UnityEnvironment.step": { "total": 0.053157956000177364, "count": 1, "is_parallel": true, "self": 0.0006968959996811463, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006791390005673748, "count": 1, "is_parallel": true, "self": 0.0006791390005673748 }, "communicator.exchange": { "total": 0.049708182999893324, "count": 1, "is_parallel": true, "self": 0.049708182999893324 }, "steps_from_proto": { "total": 0.0020737380000355188, "count": 1, "is_parallel": true, "self": 0.0003893570001309854, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016843809999045334, "count": 8, "is_parallel": true, "self": 0.0016843809999045334 } } } } } } }, "UnityEnvironment.step": { "total": 1458.7755714040331, "count": 64199, "is_parallel": true, "self": 35.262679826835665, "children": { "UnityEnvironment._generate_step_input": { "total": 24.55862793507731, "count": 64199, "is_parallel": true, "self": 24.55862793507731 }, "communicator.exchange": { "total": 1285.7376632601145, "count": 64199, "is_parallel": true, "self": 1285.7376632601145 }, "steps_from_proto": { "total": 113.21660038200571, "count": 64199, "is_parallel": true, "self": 22.551804732842356, "children": { "_process_rank_one_or_two_observation": { "total": 90.66479564916335, "count": 513592, "is_parallel": true, "self": 90.66479564916335 } } } } } } } } } } }, "trainer_advance": { "total": 681.2006386129551, "count": 64200, "self": 2.826157913771567, "children": { "process_trajectory": { "total": 118.92526791418186, "count": 64200, "self": 118.63489813118122, "children": { "RLTrainer._checkpoint": { "total": 0.2903697830006422, "count": 2, "self": 0.2903697830006422 } } }, "_update_policy": { "total": 559.4492127850017, "count": 459, "self": 364.9500068950574, "children": { "TorchPPOOptimizer.update": { "total": 194.49920588994428, "count": 22845, "self": 194.49920588994428 } } } } } } }, "trainer_threads": { "total": 1.4260003808885813e-06, "count": 1, "self": 1.4260003808885813e-06 }, "TrainerController._save_models": { "total": 0.16631428700020479, "count": 1, "self": 0.001997520999793778, "children": { "RLTrainer._checkpoint": { "total": 0.164316766000411, "count": 1, "self": 0.164316766000411 } } } } } } }