{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34996655583381653, "min": 0.3432227075099945, "max": 1.4662762880325317, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10543.7919921875, "min": 10373.5634765625, "max": 44480.95703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989942.0, "min": 29952.0, "max": 989942.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6195990443229675, "min": -0.07766404002904892, "max": 0.6195990443229675, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 174.7269287109375, "min": -18.71703338623047, "max": 174.7269287109375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0073569887317717075, "min": -0.009385962039232254, "max": 0.4073856472969055, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.0746707916259766, "min": -2.57175350189209, "max": 96.55039978027344, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07162530256097115, "min": 0.06564826246107086, "max": 0.07278591522838909, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0027542358535961, "min": 0.5042243629331692, "max": 1.0917887284258363, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014576663561109898, "min": 0.0009927405611326347, "max": 0.017291181238154724, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20407328985553858, "min": 0.011912886733591617, "max": 0.2444233798727795, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.497376072335709e-06, "min": 7.497376072335709e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010496326501269993, "min": 0.00010496326501269993, "max": 0.0035090444303185996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249909285714286, "min": 0.10249909285714286, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4349873, "min": 1.3886848, "max": 2.5696814, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002596593764285713, "min": 0.0002596593764285713, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003635231269999998, "min": 0.003635231269999998, "max": 0.11699117185999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013611873611807823, "min": 0.013611873611807823, "max": 0.5140193700790405, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.19056622684001923, "min": 0.19056622684001923, "max": 3.5981357097625732, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 324.4193548387097, "min": 315.8888888888889, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30171.0, "min": 15984.0, "max": 32605.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6325634248474592, "min": -1.0000000521540642, "max": 1.6396444239550167, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 151.8283985108137, "min": -30.356601633131504, "max": 151.8283985108137, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6325634248474592, "min": -1.0000000521540642, "max": 1.6396444239550167, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 151.8283985108137, "min": -30.356601633131504, "max": 151.8283985108137, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04612936625277163, "min": 0.04612936625277163, "max": 11.1210004594177, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.2900310615077615, "min": 4.18498034554068, "max": 177.9360073506832, "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": "1680016725", "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": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1680018870" }, "total": 2144.9299244940003, "count": 1, "self": 0.47590559699983714, "children": { "run_training.setup": { "total": 0.10975345500014555, "count": 1, "self": 0.10975345500014555 }, "TrainerController.start_learning": { "total": 2144.344265442, "count": 1, "self": 1.304164974987998, "children": { "TrainerController._reset_env": { "total": 7.236001647999956, "count": 1, "self": 7.236001647999956 }, "TrainerController.advance": { "total": 2135.695587766012, "count": 63942, "self": 1.3600496560311512, "children": { "env_step": { "total": 1513.1447930210152, "count": 63942, "self": 1406.445093993949, "children": { "SubprocessEnvManager._take_step": { "total": 105.91002619699066, "count": 63942, "self": 4.643263181010525, "children": { "TorchPolicy.evaluate": { "total": 101.26676301598013, "count": 62569, "self": 101.26676301598013 } } }, "workers": { "total": 0.7896728300754603, "count": 63942, "self": 0.0, "children": { "worker_root": { "total": 2139.9777962070452, "count": 63942, "is_parallel": true, "self": 844.4428944070901, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001675119000083214, "count": 1, "is_parallel": true, "self": 0.0005431919998954982, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011319270001877157, "count": 8, "is_parallel": true, "self": 0.0011319270001877157 } } }, "UnityEnvironment.step": { "total": 0.04866774999982226, "count": 1, "is_parallel": true, "self": 0.0005001449997052987, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045261800005391706, "count": 1, "is_parallel": true, "self": 0.00045261800005391706 }, "communicator.exchange": { "total": 0.04604857799995443, "count": 1, "is_parallel": true, "self": 0.04604857799995443 }, "steps_from_proto": { "total": 0.0016664090001086151, "count": 1, "is_parallel": true, "self": 0.0003502619999835588, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013161470001250564, "count": 8, "is_parallel": true, "self": 0.0013161470001250564 } } } } } } }, "UnityEnvironment.step": { "total": 1295.5349017999552, "count": 63941, "is_parallel": true, "self": 30.577891831843317, "children": { "UnityEnvironment._generate_step_input": { "total": 22.20192732600026, "count": 63941, "is_parallel": true, "self": 22.20192732600026 }, "communicator.exchange": { "total": 1153.5636303531026, "count": 63941, "is_parallel": true, "self": 1153.5636303531026 }, "steps_from_proto": { "total": 89.19145228900902, "count": 63941, "is_parallel": true, "self": 18.807904359965505, "children": { "_process_rank_one_or_two_observation": { "total": 70.38354792904352, "count": 511528, "is_parallel": true, "self": 70.38354792904352 } } } } } } } } } } }, "trainer_advance": { "total": 621.1907450889655, "count": 63942, "self": 2.5672509439223177, "children": { "process_trajectory": { "total": 116.21951173404887, "count": 63942, "self": 116.02119680204896, "children": { "RLTrainer._checkpoint": { "total": 0.1983149319999029, "count": 2, "self": 0.1983149319999029 } } }, "_update_policy": { "total": 502.40398241099433, "count": 454, "self": 317.65735919700865, "children": { "TorchPPOOptimizer.update": { "total": 184.74662321398569, "count": 22830, "self": 184.74662321398569 } } } } } } }, "trainer_threads": { "total": 9.509999472356867e-07, "count": 1, "self": 9.509999472356867e-07 }, "TrainerController._save_models": { "total": 0.10851010200030942, "count": 1, "self": 0.0014914410003257217, "children": { "RLTrainer._checkpoint": { "total": 0.1070186609999837, "count": 1, "self": 0.1070186609999837 } } } } } } }