{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3255844712257385, "min": 0.31013593077659607, "max": 1.3781086206436157, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9731.068359375, "min": 9415.275390625, "max": 41806.3046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989984.0, "min": 29919.0, "max": 989984.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989984.0, "min": 29919.0, "max": 989984.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.501872181892395, "min": -0.07395298779010773, "max": 0.5723642110824585, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 137.51296997070312, "min": -17.822669982910156, "max": 156.82778930664062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.027626991271972656, "min": -0.0001763963227858767, "max": 0.3662630617618561, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.569795608520508, "min": -0.047803401947021484, "max": 87.90313720703125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0689843340103641, "min": 0.06403872499775425, "max": 0.07455678087223314, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9657806761450974, "min": 0.48423895303791537, "max": 1.0645981566631235, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01500775476978604, "min": 0.0005366885280955229, "max": 0.016094081536155293, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21010856677700457, "min": 0.007513639393337322, "max": 0.24141122304232943, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.532776060535713e-06, "min": 7.532776060535713e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010545886484749998, "min": 0.00010545886484749998, "max": 0.0035084231305256993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251089285714288, "min": 0.10251089285714288, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4351525000000003, "min": 1.3886848, "max": 2.5694743000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026083819642857143, "min": 0.00026083819642857143, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036517347500000003, "min": 0.0036517347500000003, "max": 0.11697048256999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01327251922339201, "min": 0.01327251922339201, "max": 0.4591746926307678, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18581527471542358, "min": 0.18581527471542358, "max": 3.2142229080200195, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 388.75949367088606, "min": 334.89772727272725, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30712.0, "min": 17613.0, "max": 32286.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5352556779037547, "min": -0.9999667187531789, "max": 1.600337056045452, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 121.28519855439663, "min": -29.999001562595367, "max": 142.42999798804522, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5352556779037547, "min": -0.9999667187531789, "max": 1.600337056045452, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 121.28519855439663, "min": -29.999001562595367, "max": 142.42999798804522, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.053791625220387516, "min": 0.047308317608634284, "max": 7.801062280519141, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.249538392410614, "min": 3.997737094759941, "max": 140.41912104934454, "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": "1771816479", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1771818733" }, "total": 2253.22692818, "count": 1, "self": 0.4831814719996146, "children": { "run_training.setup": { "total": 0.025376862000030087, "count": 1, "self": 0.025376862000030087 }, "TrainerController.start_learning": { "total": 2252.7183698460003, "count": 1, "self": 1.4973978150355833, "children": { "TrainerController._reset_env": { "total": 3.1093459159999384, "count": 1, "self": 3.1093459159999384 }, "TrainerController.advance": { "total": 2248.0236739759644, "count": 63863, "self": 1.5050557559247864, "children": { "env_step": { "total": 1578.7381387430476, "count": 63863, "self": 1422.17371014123, "children": { "SubprocessEnvManager._take_step": { "total": 155.69077253888895, "count": 63863, "self": 4.718531647911732, "children": { "TorchPolicy.evaluate": { "total": 150.97224089097722, "count": 62551, "self": 150.97224089097722 } } }, "workers": { "total": 0.8736560629286032, "count": 63863, "self": 0.0, "children": { "worker_root": { "total": 2246.083867580876, "count": 63863, "is_parallel": true, "self": 943.105925030836, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004622982000000775, "count": 1, "is_parallel": true, "self": 0.0033170359997711785, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013059460002295964, "count": 8, "is_parallel": true, "self": 0.0013059460002295964 } } }, "UnityEnvironment.step": { "total": 0.048196236999956454, "count": 1, "is_parallel": true, "self": 0.000615137000067989, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005553999999392545, "count": 1, "is_parallel": true, "self": 0.0005553999999392545 }, "communicator.exchange": { "total": 0.045378588999938074, "count": 1, "is_parallel": true, "self": 0.045378588999938074 }, "steps_from_proto": { "total": 0.0016471110000111366, "count": 1, "is_parallel": true, "self": 0.00041652599975350313, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012305850002576335, "count": 8, "is_parallel": true, "self": 0.0012305850002576335 } } } } } } }, "UnityEnvironment.step": { "total": 1302.9779425500399, "count": 63862, "is_parallel": true, "self": 34.586741751097634, "children": { "UnityEnvironment._generate_step_input": { "total": 22.928530294992925, "count": 63862, "is_parallel": true, "self": 22.928530294992925 }, "communicator.exchange": { "total": 1140.4839699329714, "count": 63862, "is_parallel": true, "self": 1140.4839699329714 }, "steps_from_proto": { "total": 104.97870057097794, "count": 63862, "is_parallel": true, "self": 22.47106259813586, "children": { "_process_rank_one_or_two_observation": { "total": 82.50763797284208, "count": 510896, "is_parallel": true, "self": 82.50763797284208 } } } } } } } } } } }, "trainer_advance": { "total": 667.780479476992, "count": 63863, "self": 2.791470568052773, "children": { "process_trajectory": { "total": 124.02776961294126, "count": 63863, "self": 123.76675009694031, "children": { "RLTrainer._checkpoint": { "total": 0.26101951600094253, "count": 2, "self": 0.26101951600094253 } } }, "_update_policy": { "total": 540.961239295998, "count": 454, "self": 297.62305236303405, "children": { "TorchPPOOptimizer.update": { "total": 243.33818693296394, "count": 22836, "self": 243.33818693296394 } } } } } } }, "trainer_threads": { "total": 8.750002962187864e-07, "count": 1, "self": 8.750002962187864e-07 }, "TrainerController._save_models": { "total": 0.08795126400036679, "count": 1, "self": 0.001021961000333249, "children": { "RLTrainer._checkpoint": { "total": 0.08692930300003354, "count": 1, "self": 0.08692930300003354 } } } } } } }