{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.35682806372642517, "min": 0.3346475064754486, "max": 1.5512598752975464, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10721.9697265625, "min": 9980.52734375, "max": 47059.01953125, "count": 33 }, "Pyramids.Step.mean": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989912.0, "min": 29952.0, "max": 989912.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.45596837997436523, "min": -0.16926656663417816, "max": 0.53659987449646, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 123.56742858886719, "min": -40.793243408203125, "max": 147.56497192382812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006324374116957188, "min": 0.0007141218520700932, "max": 0.3233257532119751, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.7139053344726562, "min": 0.17995870113372803, "max": 76.62820434570312, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06850312618238406, "min": 0.06446809135506756, "max": 0.0735797237087455, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9590437665533769, "min": 0.4635333114433445, "max": 1.1036958556311827, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01484861157461805, "min": 0.0009923496977111712, "max": 0.01583887216192023, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20788056204465272, "min": 0.009820871781770641, "max": 0.23758308242880347, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.50946178259286e-06, "min": 7.50946178259286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010513246495630003, "min": 0.00010513246495630003, "max": 0.0036327256890915003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250312142857143, "min": 0.10250312142857143, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4350437, "min": 1.3691136000000002, "max": 2.6109084999999994, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026006183071428584, "min": 0.00026006183071428584, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003640865630000002, "min": 0.003640865630000002, "max": 0.12110975915000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009745752438902855, "min": 0.009745752438902855, "max": 0.3064081072807312, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13644053041934967, "min": 0.13644053041934967, "max": 2.1448566913604736, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 378.4578313253012, "min": 361.5357142857143, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31412.0, "min": 15984.0, "max": 32674.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4527999835919185, "min": -1.0000000521540642, "max": 1.5391132360301822, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 120.58239863812923, "min": -32.000001668930054, "max": 127.74639859050512, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4527999835919185, "min": -1.0000000521540642, "max": 1.5391132360301822, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 120.58239863812923, "min": -32.000001668930054, "max": 127.74639859050512, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03833495598449091, "min": 0.03833495598449091, "max": 6.116671589203179, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.1818013467127457, "min": 3.0807472558808513, "max": 97.86674542725086, "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": "1678385758", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1.8.1+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1678388019" }, "total": 2260.1201356200004, "count": 1, "self": 0.4896350649996748, "children": { "run_training.setup": { "total": 0.11159209700008432, "count": 1, "self": 0.11159209700008432 }, "TrainerController.start_learning": { "total": 2259.5189084580006, "count": 1, "self": 1.2800288019188883, "children": { "TrainerController._reset_env": { "total": 7.9300925560000906, "count": 1, "self": 7.9300925560000906 }, "TrainerController.advance": { "total": 2250.2212998970817, "count": 63752, "self": 1.383713854985217, "children": { "env_step": { "total": 1594.1237894040169, "count": 63752, "self": 1481.520211151087, "children": { "SubprocessEnvManager._take_step": { "total": 111.80907257999797, "count": 63752, "self": 5.272573593028028, "children": { "TorchPolicy.evaluate": { "total": 106.53649898696995, "count": 62573, "self": 106.53649898696995 } } }, "workers": { "total": 0.7945056729317912, "count": 63752, "self": 0.0, "children": { "worker_root": { "total": 2254.5585236978845, "count": 63752, "is_parallel": true, "self": 888.9097621558703, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017153399999187968, "count": 1, "is_parallel": true, "self": 0.0005261480000626761, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011891919998561207, "count": 8, "is_parallel": true, "self": 0.0011891919998561207 } } }, "UnityEnvironment.step": { "total": 0.06701120400020955, "count": 1, "is_parallel": true, "self": 0.0005011110001760244, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004635539999071625, "count": 1, "is_parallel": true, "self": 0.0004635539999071625 }, "communicator.exchange": { "total": 0.06450139399976251, "count": 1, "is_parallel": true, "self": 0.06450139399976251 }, "steps_from_proto": { "total": 0.0015451450003638456, "count": 1, "is_parallel": true, "self": 0.000391345000025467, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011538000003383786, "count": 8, "is_parallel": true, "self": 0.0011538000003383786 } } } } } } }, "UnityEnvironment.step": { "total": 1365.6487615420142, "count": 63751, "is_parallel": true, "self": 31.706104959838285, "children": { "UnityEnvironment._generate_step_input": { "total": 23.044795234070534, "count": 63751, "is_parallel": true, "self": 23.044795234070534 }, "communicator.exchange": { "total": 1217.0899062100789, "count": 63751, "is_parallel": true, "self": 1217.0899062100789 }, "steps_from_proto": { "total": 93.8079551380265, "count": 63751, "is_parallel": true, "self": 19.55370439799708, "children": { "_process_rank_one_or_two_observation": { "total": 74.25425074002942, "count": 510008, "is_parallel": true, "self": 74.25425074002942 } } } } } } } } } } }, "trainer_advance": { "total": 654.7137966380797, "count": 63752, "self": 2.482613568177385, "children": { "process_trajectory": { "total": 121.36867368890171, "count": 63752, "self": 121.12749515190262, "children": { "RLTrainer._checkpoint": { "total": 0.24117853699908665, "count": 2, "self": 0.24117853699908665 } } }, "_update_policy": { "total": 530.8625093810006, "count": 450, "self": 335.8394470780263, "children": { "TorchPPOOptimizer.update": { "total": 195.02306230297427, "count": 22839, "self": 195.02306230297427 } } } } } } }, "trainer_threads": { "total": 1.1500005712150596e-06, "count": 1, "self": 1.1500005712150596e-06 }, "TrainerController._save_models": { "total": 0.08748605299933843, "count": 1, "self": 0.001473029999033315, "children": { "RLTrainer._checkpoint": { "total": 0.08601302300030511, "count": 1, "self": 0.08601302300030511 } } } } } } }