{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.6383645534515381, "min": 0.615313708782196, "max": 0.9496520161628723, "count": 14 }, "Pyramids.Policy.Entropy.sum": { "value": 19222.43359375, "min": 11669.32421875, "max": 26354.03515625, "count": 14 }, "Pyramids.Step.mean": { "value": 989978.0, "min": 599996.0, "max": 989978.0, "count": 14 }, "Pyramids.Step.sum": { "value": 989978.0, "min": 599996.0, "max": 989978.0, "count": 14 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3585755527019501, "min": 0.19249166548252106, "max": 0.4474329352378845, "count": 14 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 96.45682525634766, "min": 18.28670883178711, "max": 121.25432586669922, "count": 14 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.002819396322593093, "min": -0.04338645190000534, "max": 0.04091056063771248, "count": 14 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.7584176063537598, "min": -11.540796279907227, "max": 10.30946159362793, "count": 14 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06751222568079053, "min": 0.06751222568079053, "max": 0.07376259519341623, "count": 14 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.012683385211858, "min": 0.2913393726533589, "max": 1.0558086735220378, "count": 14 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012618124234399552, "min": 0.008346661679431289, "max": 0.013856102255522276, "count": 14 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18927186351599326, "min": 0.042184563068682714, "max": 0.20784153383283413, "count": 14 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.468857510413333e-06, "min": 7.468857510413333e-06, "max": 0.000121194284601925, "count": 14 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011203286265619999, "min": 0.00011203286265619999, "max": 0.0016174508608499997, "count": 14 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248958666666669, "min": 0.10248958666666669, "max": 0.140398075, "count": 14 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373438000000004, "min": 0.5615923, "max": 1.9875115000000003, "count": 14 }, "Pyramids.Policy.Beta.mean": { "value": 0.000258709708, "min": 0.000258709708, "max": 0.0040457676925000005, "count": 14 }, "Pyramids.Policy.Beta.sum": { "value": 0.00388064562, "min": 0.00388064562, "max": 0.054001085000000004, "count": 14 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007297104224562645, "min": 0.007063571363687515, "max": 0.00979213509708643, "count": 14 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10945656150579453, "min": 0.036756519228219986, "max": 0.13708989322185516, "count": 14 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 458.28985507246375, "min": 406.07142857142856, "max": 691.2083333333334, "count": 14 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31622.0, "min": 5685.0, "max": 33285.0, "count": 14 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3097391133939011, "min": 0.7194212434139657, "max": 1.5939285733870097, "count": 14 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 90.37199882417917, "min": 22.315000027418137, "max": 105.12839791178703, "count": 14 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3097391133939011, "min": 0.7194212434139657, "max": 1.5939285733870097, "count": 14 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 90.37199882417917, "min": 22.315000027418137, "max": 105.12839791178703, "count": 14 }, "Pyramids.Policy.RndReward.mean": { "value": 0.035147823929234975, "min": 0.03444063365361162, "max": 0.06344039772235927, "count": 14 }, "Pyramids.Policy.RndReward.sum": { "value": 2.4251998511172133, "min": 0.6170701496885158, "max": 2.9816986929508857, "count": 14 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 14 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 14 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1727790776", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", "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 --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727792160" }, "total": 1383.7806088080001, "count": 1, "self": 1.093362913999954, "children": { "run_training.setup": { "total": 0.06807297000023027, "count": 1, "self": 0.06807297000023027 }, "TrainerController.start_learning": { "total": 1382.619172924, "count": 1, "self": 0.983062282969513, "children": { "TrainerController._reset_env": { "total": 2.1543254119997073, "count": 1, "self": 2.1543254119997073 }, "TrainerController.advance": { "total": 1379.3588168690308, "count": 26385, "self": 1.0767953870554265, "children": { "env_step": { "total": 918.1965111289596, "count": 26385, "self": 848.5186319479626, "children": { "SubprocessEnvManager._take_step": { "total": 69.08725790203334, "count": 26385, "self": 2.855913230971055, "children": { "TorchPolicy.evaluate": { "total": 66.23134467106229, "count": 25754, "self": 66.23134467106229 } } }, "workers": { "total": 0.5906212789636811, "count": 26385, "self": 0.0, "children": { "worker_root": { "total": 1379.4988767559962, "count": 26385, "is_parallel": true, "self": 607.3597904190356, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023493080002481292, "count": 1, "is_parallel": true, "self": 0.0007643160006409744, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015849919996071549, "count": 8, "is_parallel": true, "self": 0.0015849919996071549 } } }, "UnityEnvironment.step": { "total": 0.10993950900001437, "count": 1, "is_parallel": true, "self": 0.0007298159998754272, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005087030003778636, "count": 1, "is_parallel": true, "self": 0.0005087030003778636 }, "communicator.exchange": { "total": 0.10678818999986106, "count": 1, "is_parallel": true, "self": 0.10678818999986106 }, "steps_from_proto": { "total": 0.0019127999999000167, "count": 1, "is_parallel": true, "self": 0.00037291599983291235, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015398840000671044, "count": 8, "is_parallel": true, "self": 0.0015398840000671044 } } } } } } }, "UnityEnvironment.step": { "total": 772.1390863369606, "count": 26384, "is_parallel": true, "self": 20.45920139788086, "children": { "UnityEnvironment._generate_step_input": { "total": 12.708429189027811, "count": 26384, "is_parallel": true, "self": 12.708429189027811 }, "communicator.exchange": { "total": 684.5895122230281, "count": 26384, "is_parallel": true, "self": 684.5895122230281 }, "steps_from_proto": { "total": 54.38194352702385, "count": 26384, "is_parallel": true, "self": 11.872298791948197, "children": { "_process_rank_one_or_two_observation": { "total": 42.50964473507565, "count": 211072, "is_parallel": true, "self": 42.50964473507565 } } } } } } } } } } }, "trainer_advance": { "total": 460.0855103530157, "count": 26385, "self": 1.9452249829837456, "children": { "process_trajectory": { "total": 70.24383431303158, "count": 26385, "self": 70.09436840103172, "children": { "RLTrainer._checkpoint": { "total": 0.1494659119998687, "count": 1, "self": 0.1494659119998687 } } }, "_update_policy": { "total": 387.8964510570004, "count": 193, "self": 156.383977185008, "children": { "TorchPPOOptimizer.update": { "total": 231.51247387199237, "count": 9339, "self": 231.51247387199237 } } } } } } }, "trainer_threads": { "total": 1.8300002011528704e-06, "count": 1, "self": 1.8300002011528704e-06 }, "TrainerController._save_models": { "total": 0.12296652999975777, "count": 1, "self": 0.005349126999590226, "children": { "RLTrainer._checkpoint": { "total": 0.11761740300016754, "count": 1, "self": 0.11761740300016754 } } } } } } }