{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13928763568401337, "min": 0.12780652940273285, "max": 1.2807379961013794, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4169.71484375, "min": 3826.016357421875, "max": 38852.46875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999934.0, "min": 29952.0, "max": 2999934.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999934.0, "min": 29952.0, "max": 2999934.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8309884667396545, "min": -0.10247080773115158, "max": 0.896207332611084, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 250.12753295898438, "min": -24.695465087890625, "max": 276.88299560546875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013022739440202713, "min": -0.016558533534407616, "max": 0.48631641268730164, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.919844627380371, "min": -4.917884349822998, "max": 115.25698852539062, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06496028542113934, "min": 0.06372973365036563, "max": 0.07358708845900505, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9094439958959507, "min": 0.4893185659509083, "max": 1.0906294951661644, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015281590343441901, "min": 0.00018003048219995707, "max": 0.01705909237562821, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21394226480818662, "min": 0.002340396268599442, "max": 0.23882729325879495, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5315137752428576e-06, "min": 1.5315137752428576e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1441192853400008e-05, "min": 2.1441192853400008e-05, "max": 0.004072650542449867, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051047142857143, "min": 0.10051047142857143, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071466000000001, "min": 1.3962282666666668, "max": 2.857550133333333, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.099609571428574e-05, "min": 6.099609571428574e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008539453400000003, "min": 0.0008539453400000003, "max": 0.13576925832, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007508373353630304, "min": 0.007421405054628849, "max": 0.6217107176780701, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10511722415685654, "min": 0.10389967262744904, "max": 4.351974964141846, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 225.22222222222223, "min": 200.62237762237763, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30405.0, "min": 15984.0, "max": 33170.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7599614725068764, "min": -1.0000000521540642, "max": 1.800181807337941, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 237.5947987884283, "min": -31.994401648640633, "max": 269.4269982278347, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7599614725068764, "min": -1.0000000521540642, "max": 1.800181807337941, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 237.5947987884283, "min": -31.994401648640633, "max": 269.4269982278347, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017902067269002415, "min": 0.01700685322521841, "max": 12.416862834244967, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.416779081315326, "min": 2.295925185404485, "max": 198.66980534791946, "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": "1688519502", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/home/raj/repos/HF-DeepRL/.venv/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+cu113", "numpy_version": "1.21.2", "end_time_seconds": "1688523006" }, "total": 3504.277956400001, "count": 1, "self": 0.2179591000021901, "children": { "run_training.setup": { "total": 0.008524900003976654, "count": 1, "self": 0.008524900003976654 }, "TrainerController.start_learning": { "total": 3504.051472399995, "count": 1, "self": 2.0971406017415575, "children": { "TrainerController._reset_env": { "total": 3.082370299998729, "count": 1, "self": 3.082370299998729 }, "TrainerController.advance": { "total": 3498.7905649982567, "count": 195671, "self": 1.9226020994683495, "children": { "env_step": { "total": 1887.3278812998979, "count": 195671, "self": 1401.84359939953, "children": { "SubprocessEnvManager._take_step": { "total": 484.26212249904347, "count": 195671, "self": 6.693297200654342, "children": { "TorchPolicy.evaluate": { "total": 477.56882529838913, "count": 187557, "self": 477.56882529838913 } } }, "workers": { "total": 1.2221594013244612, "count": 195671, "self": 0.0, "children": { "worker_root": { "total": 3498.7065126990346, "count": 195671, "is_parallel": true, "self": 2236.411058497826, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008710999973118305, "count": 1, "is_parallel": true, "self": 0.00027830000180983916, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005927999955019914, "count": 8, "is_parallel": true, "self": 0.0005927999955019914 } } }, "UnityEnvironment.step": { "total": 0.017862200002127793, "count": 1, "is_parallel": true, "self": 0.00020080000103916973, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020470000163186342, "count": 1, "is_parallel": true, "self": 0.00020470000163186342 }, "communicator.exchange": { "total": 0.016845099999045487, "count": 1, "is_parallel": true, "self": 0.016845099999045487 }, "steps_from_proto": { "total": 0.000611600000411272, "count": 1, "is_parallel": true, "self": 0.0001469999915570952, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046460000885417685, "count": 8, "is_parallel": true, "self": 0.00046460000885417685 } } } } } } }, "UnityEnvironment.step": { "total": 1262.2954542012085, "count": 195670, "is_parallel": true, "self": 32.163789501857536, "children": { "UnityEnvironment._generate_step_input": { "total": 25.195674999085895, "count": 195670, "is_parallel": true, "self": 25.195674999085895 }, "communicator.exchange": { "total": 1111.9657235010527, "count": 195670, "is_parallel": true, "self": 1111.9657235010527 }, "steps_from_proto": { "total": 92.97026619921235, "count": 195670, "is_parallel": true, "self": 20.97025329810276, "children": { "_process_rank_one_or_two_observation": { "total": 72.00001290110959, "count": 1565360, "is_parallel": true, "self": 72.00001290110959 } } } } } } } } } } }, "trainer_advance": { "total": 1609.5400815988905, "count": 195671, "self": 4.413734699061024, "children": { "process_trajectory": { "total": 291.8460889999624, "count": 195671, "self": 291.35634229996504, "children": { "RLTrainer._checkpoint": { "total": 0.48974669999734033, "count": 6, "self": 0.48974669999734033 } } }, "_update_policy": { "total": 1313.2802578998671, "count": 1400, "self": 646.1147149000026, "children": { "TorchPPOOptimizer.update": { "total": 667.1655429998646, "count": 68448, "self": 667.1655429998646 } } } } } } }, "trainer_threads": { "total": 5.999972927384079e-07, "count": 1, "self": 5.999972927384079e-07 }, "TrainerController._save_models": { "total": 0.08139590000064345, "count": 1, "self": 0.0005328999977791682, "children": { "RLTrainer._checkpoint": { "total": 0.08086300000286428, "count": 1, "self": 0.08086300000286428 } } } } } } }