{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.42758989334106445, "min": 0.42758989334106445, "max": 1.4461727142333984, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12690.8681640625, "min": 12690.8681640625, "max": 43871.09375, "count": 33 }, "Pyramids.Step.mean": { "value": 989984.0, "min": 29952.0, "max": 989984.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989984.0, "min": 29952.0, "max": 989984.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5934091210365295, "min": -0.273622989654541, "max": 0.6837636232376099, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 168.52818298339844, "min": -64.84864807128906, "max": 198.29144287109375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010817230679094791, "min": -0.01882975548505783, "max": 0.3778967559337616, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.0720934867858887, "min": -4.820417404174805, "max": 90.69522094726562, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06779025985451881, "min": 0.0662851044096882, "max": 0.07208812630103369, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9490636379632633, "min": 0.4970090431748319, "max": 1.0704097336400118, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016994939831506815, "min": 0.0013944531509351207, "max": 0.017960946889232016, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2379291576410954, "min": 0.011155625207480965, "max": 0.26941420333848026, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4211332406071425e-06, "min": 7.4211332406071425e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001038958653685, "min": 0.0001038958653685, "max": 0.003632421189192999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247367857142857, "min": 0.10247367857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346315, "min": 1.3886848, "max": 2.6108070000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025712048928571427, "min": 0.00025712048928571427, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035996868499999996, "min": 0.0035996868499999996, "max": 0.12109961929999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009640991687774658, "min": 0.009284255094826221, "max": 0.4445316791534424, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13497388362884521, "min": 0.12997956573963165, "max": 3.1117217540740967, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 296.6224489795918, "min": 276.76, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29069.0, "min": 15984.0, "max": 32482.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.662546919164609, "min": -1.0000000521540642, "max": 1.72323998183012, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 162.92959807813168, "min": -30.50600166618824, "max": 182.6529991030693, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.662546919164609, "min": -1.0000000521540642, "max": 1.72323998183012, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 162.92959807813168, "min": -30.50600166618824, "max": 182.6529991030693, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.029869763423689896, "min": 0.027865388850292425, "max": 8.3350789565593, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.92723681552161, "min": 2.765795480227098, "max": 133.3612633049488, "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": "1679708300", "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": "1679710537" }, "total": 2237.291220442, "count": 1, "self": 0.4895249689998309, "children": { "run_training.setup": { "total": 0.10079495299999053, "count": 1, "self": 0.10079495299999053 }, "TrainerController.start_learning": { "total": 2236.7009005200002, "count": 1, "self": 1.4235971989792233, "children": { "TrainerController._reset_env": { "total": 5.958445549999965, "count": 1, "self": 5.958445549999965 }, "TrainerController.advance": { "total": 2229.226612100021, "count": 64228, "self": 1.5049944279890042, "children": { "env_step": { "total": 1589.2613435730177, "count": 64228, "self": 1475.878499582005, "children": { "SubprocessEnvManager._take_step": { "total": 112.50375128604014, "count": 64228, "self": 4.935519851073877, "children": { "TorchPolicy.evaluate": { "total": 107.56823143496626, "count": 62572, "self": 107.56823143496626 } } }, "workers": { "total": 0.8790927049726633, "count": 64228, "self": 0.0, "children": { "worker_root": { "total": 2231.598077420989, "count": 64228, "is_parallel": true, "self": 878.9080344209767, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018666849999817714, "count": 1, "is_parallel": true, "self": 0.0005537649999496352, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013129200000321362, "count": 8, "is_parallel": true, "self": 0.0013129200000321362 } } }, "UnityEnvironment.step": { "total": 0.04732788800004073, "count": 1, "is_parallel": true, "self": 0.0005864839999958349, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000486503000047378, "count": 1, "is_parallel": true, "self": 0.000486503000047378 }, "communicator.exchange": { "total": 0.04447348799999418, "count": 1, "is_parallel": true, "self": 0.04447348799999418 }, "steps_from_proto": { "total": 0.0017814130000033401, "count": 1, "is_parallel": true, "self": 0.0004191080000737202, "children": { "_process_rank_one_or_two_observation": { "total": 0.00136230499992962, "count": 8, "is_parallel": true, "self": 0.00136230499992962 } } } } } } }, "UnityEnvironment.step": { "total": 1352.690043000012, "count": 64227, "is_parallel": true, "self": 31.486624373083714, "children": { "UnityEnvironment._generate_step_input": { "total": 24.158403278955802, "count": 64227, "is_parallel": true, "self": 24.158403278955802 }, "communicator.exchange": { "total": 1200.2466605240165, "count": 64227, "is_parallel": true, "self": 1200.2466605240165 }, "steps_from_proto": { "total": 96.79835482395595, "count": 64227, "is_parallel": true, "self": 21.096120239850507, "children": { "_process_rank_one_or_two_observation": { "total": 75.70223458410544, "count": 513816, "is_parallel": true, "self": 75.70223458410544 } } } } } } } } } } }, "trainer_advance": { "total": 638.4602740990146, "count": 64228, "self": 2.813739673975533, "children": { "process_trajectory": { "total": 125.94176474003996, "count": 64228, "self": 125.74021073303982, "children": { "RLTrainer._checkpoint": { "total": 0.2015540070001407, "count": 2, "self": 0.2015540070001407 } } }, "_update_policy": { "total": 509.70476968499906, "count": 453, "self": 325.10835998795994, "children": { "TorchPPOOptimizer.update": { "total": 184.59640969703912, "count": 22830, "self": 184.59640969703912 } } } } } } }, "trainer_threads": { "total": 9.4600000011269e-07, "count": 1, "self": 9.4600000011269e-07 }, "TrainerController._save_models": { "total": 0.09224472500000047, "count": 1, "self": 0.0013783819999844127, "children": { "RLTrainer._checkpoint": { "total": 0.09086634300001606, "count": 1, "self": 0.09086634300001606 } } } } } } }