{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.1587962955236435, "min": 0.1474454551935196, "max": 1.4695897102355957, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4779.13330078125, "min": 4463.46875, "max": 44581.47265625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999991.0, "min": 29939.0, "max": 2999991.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999991.0, "min": 29939.0, "max": 2999991.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7377570867538452, "min": -0.11414249241352081, "max": 0.7987221479415894, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 222.80264282226562, "min": -27.622482299804688, "max": 240.4153594970703, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0076134828850626945, "min": -0.10480871796607971, "max": 0.19369041919708252, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.299271821975708, "min": -27.564693450927734, "max": 46.67938995361328, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06885544028700068, "min": 0.0628889797468825, "max": 0.0741502790271105, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9639761640180095, "min": 0.568270428708689, "max": 1.0793839644951124, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01937868855481104, "min": 0.0004330306973345873, "max": 0.01937868855481104, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.27130163976735455, "min": 0.005196368368015048, "max": 0.27130163976735455, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5755780462690433e-06, "min": 1.5755780462690433e-06, "max": 0.00029828048807317085, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2058092647766606e-05, "min": 2.2058092647766606e-05, "max": 0.003885367204877633, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052515952380954, "min": 0.10052515952380954, "max": 0.1994268291666667, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4073522333333335, "min": 1.4073522333333335, "max": 2.7674702666666664, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.246343642857128e-05, "min": 6.246343642857128e-05, "max": 0.00994274023375, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008744881099999979, "min": 0.0008744881099999979, "max": 0.12952272442999999, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005305563099682331, "min": 0.004741419106721878, "max": 0.29868173599243164, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07427788525819778, "min": 0.06637986749410629, "max": 2.389453887939453, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 241.1796875, "min": 230.29850746268656, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30871.0, "min": 16354.0, "max": 32568.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7591015553334728, "min": -0.9999375520274043, "max": 1.7591015553334728, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 225.16499908268452, "min": -31.998001664876938, "max": 227.47259797900915, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7591015553334728, "min": -0.9999375520274043, "max": 1.7591015553334728, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 225.16499908268452, "min": -31.998001664876938, "max": 227.47259797900915, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01318188088248462, "min": 0.012151102597791967, "max": 5.177931000204647, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6872807529580314, "min": 1.4533254647267313, "max": 88.024827003479, "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": "1724659805", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724667316" }, "total": 7510.207491495999, "count": 1, "self": 0.4997617059998447, "children": { "run_training.setup": { "total": 0.06066367999983413, "count": 1, "self": 0.06066367999983413 }, "TrainerController.start_learning": { "total": 7509.647066109999, "count": 1, "self": 4.456238086896519, "children": { "TrainerController._reset_env": { "total": 3.1007353200000125, "count": 1, "self": 3.1007353200000125 }, "TrainerController.advance": { "total": 7501.994979020102, "count": 194437, "self": 4.700116860056369, "children": { "env_step": { "total": 5359.6241350891505, "count": 194437, "self": 4880.849109645327, "children": { "SubprocessEnvManager._take_step": { "total": 476.02471391701647, "count": 194437, "self": 14.578287598365023, "children": { "TorchPolicy.evaluate": { "total": 461.44642631865145, "count": 187559, "self": 461.44642631865145 } } }, "workers": { "total": 2.750311526807309, "count": 194437, "self": 0.0, "children": { "worker_root": { "total": 7494.0992139968985, "count": 194437, "is_parallel": true, "self": 2992.7259641959836, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005411172999856717, "count": 1, "is_parallel": true, "self": 0.0038792319996900915, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015319410001666256, "count": 8, "is_parallel": true, "self": 0.0015319410001666256 } } }, "UnityEnvironment.step": { "total": 0.05124529099998654, "count": 1, "is_parallel": true, "self": 0.0006496000000879576, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043016499989789736, "count": 1, "is_parallel": true, "self": 0.00043016499989789736 }, "communicator.exchange": { "total": 0.04852582299986352, "count": 1, "is_parallel": true, "self": 0.04852582299986352 }, "steps_from_proto": { "total": 0.0016397030001371604, "count": 1, "is_parallel": true, "self": 0.0003547730002537719, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012849299998833885, "count": 8, "is_parallel": true, "self": 0.0012849299998833885 } } } } } } }, "UnityEnvironment.step": { "total": 4501.373249800915, "count": 194436, "is_parallel": true, "self": 104.68144598912113, "children": { "UnityEnvironment._generate_step_input": { "total": 69.90246594258542, "count": 194436, "is_parallel": true, "self": 69.90246594258542 }, "communicator.exchange": { "total": 4027.1333846233615, "count": 194436, "is_parallel": true, "self": 4027.1333846233615 }, "steps_from_proto": { "total": 299.65595324584706, "count": 194436, "is_parallel": true, "self": 62.10770851803545, "children": { "_process_rank_one_or_two_observation": { "total": 237.5482447278116, "count": 1555488, "is_parallel": true, "self": 237.5482447278116 } } } } } } } } } } }, "trainer_advance": { "total": 2137.670727070895, "count": 194437, "self": 9.43775802807886, "children": { "process_trajectory": { "total": 421.8030710518133, "count": 194437, "self": 421.06919726181104, "children": { "RLTrainer._checkpoint": { "total": 0.7338737900022352, "count": 6, "self": 0.7338737900022352 } } }, "_update_policy": { "total": 1706.4298979910027, "count": 1399, "self": 960.0585374229372, "children": { "TorchPPOOptimizer.update": { "total": 746.3713605680655, "count": 68376, "self": 746.3713605680655 } } } } } } }, "trainer_threads": { "total": 8.780007192399353e-07, "count": 1, "self": 8.780007192399353e-07 }, "TrainerController._save_models": { "total": 0.09511280500009889, "count": 1, "self": 0.001783863001037389, "children": { "RLTrainer._checkpoint": { "total": 0.0933289419990615, "count": 1, "self": 0.0933289419990615 } } } } } } }