{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13876710832118988, "min": 0.13432703912258148, "max": 1.4431456327438354, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4163.01318359375, "min": 3999.721923828125, "max": 43779.265625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999952.0, "min": 29952.0, "max": 2999952.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999952.0, "min": 29952.0, "max": 2999952.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7671077847480774, "min": -0.09470533579587936, "max": 0.8931918144226074, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 229.36521911621094, "min": -22.823986053466797, "max": 277.78265380859375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01043110154569149, "min": -0.006275723688304424, "max": 0.29345884919166565, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.118899345397949, "min": -1.7697540521621704, "max": 71.01704406738281, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06964342983895118, "min": 0.06385245280121342, "max": 0.07293927091575166, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9750080177453164, "min": 0.5105748964102615, "max": 1.0909466995411397, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014652011885184791, "min": 0.0006142910788328597, "max": 0.017098186246829673, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20512816639258707, "min": 0.007371492945994316, "max": 0.23937460745561542, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4867423615952352e-06, "min": 1.4867423615952352e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0814393062333293e-05, "min": 2.0814393062333293e-05, "max": 0.003885709104763666, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049554761904762, "min": 0.10049554761904762, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069376666666666, "min": 1.3962282666666668, "max": 2.7674063000000007, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.950520714285704e-05, "min": 5.950520714285704e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008330728999999986, "min": 0.0008330728999999986, "max": 0.1295341097, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007789392955601215, "min": 0.007733598817139864, "max": 0.407003790140152, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10905150324106216, "min": 0.10905150324106216, "max": 2.8490264415740967, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 240.4126984126984, "min": 200.75862068965517, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30292.0, "min": 15984.0, "max": 33260.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7278269747538226, "min": -1.0000000521540642, "max": 1.7992413723263248, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 217.70619881898165, "min": -29.646601662039757, "max": 260.8899989873171, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7278269747538226, "min": -1.0000000521540642, "max": 1.7992413723263248, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 217.70619881898165, "min": -29.646601662039757, "max": 260.8899989873171, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01933080858829531, "min": 0.017162133163796608, "max": 7.941678044386208, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.435681882125209, "min": 2.383856428648869, "max": 127.06684871017933, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1754525139", "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": "1754533342" }, "total": 8203.843653866, "count": 1, "self": 0.8039714570022625, "children": { "run_training.setup": { "total": 0.034641508999811776, "count": 1, "self": 0.034641508999811776 }, "TrainerController.start_learning": { "total": 8203.0050409, "count": 1, "self": 6.737941871904695, "children": { "TrainerController._reset_env": { "total": 2.5241286079999554, "count": 1, "self": 2.5241286079999554 }, "TrainerController.advance": { "total": 8193.674836213095, "count": 195364, "self": 5.959284256076899, "children": { "env_step": { "total": 5851.940889743002, "count": 195364, "self": 5426.916999434334, "children": { "SubprocessEnvManager._take_step": { "total": 420.6415295159768, "count": 195364, "self": 14.478455594885418, "children": { "TorchPolicy.evaluate": { "total": 406.1630739210914, "count": 187558, "self": 406.1630739210914 } } }, "workers": { "total": 4.382360792691998, "count": 195364, "self": 0.0, "children": { "worker_root": { "total": 8183.503185791825, "count": 195364, "is_parallel": true, "self": 3208.7013997880567, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0037894600000072387, "count": 1, "is_parallel": true, "self": 0.0014757799999642884, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023136800000429503, "count": 8, "is_parallel": true, "self": 0.0023136800000429503 } } }, "UnityEnvironment.step": { "total": 0.05219711700010521, "count": 1, "is_parallel": true, "self": 0.0004992100002709776, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004546390000541578, "count": 1, "is_parallel": true, "self": 0.0004546390000541578 }, "communicator.exchange": { "total": 0.049542387999963466, "count": 1, "is_parallel": true, "self": 0.049542387999963466 }, "steps_from_proto": { "total": 0.0017008799998166069, "count": 1, "is_parallel": true, "self": 0.0003099890000157757, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013908909998008312, "count": 8, "is_parallel": true, "self": 0.0013908909998008312 } } } } } } }, "UnityEnvironment.step": { "total": 4974.801786003768, "count": 195363, "is_parallel": true, "self": 106.05013710134244, "children": { "UnityEnvironment._generate_step_input": { "total": 75.61579609580122, "count": 195363, "is_parallel": true, "self": 75.61579609580122 }, "communicator.exchange": { "total": 4503.694490661891, "count": 195363, "is_parallel": true, "self": 4503.694490661891 }, "steps_from_proto": { "total": 289.4413621447329, "count": 195363, "is_parallel": true, "self": 65.14290618706923, "children": { "_process_rank_one_or_two_observation": { "total": 224.2984559576637, "count": 1562904, "is_parallel": true, "self": 224.2984559576637 } } } } } } } } } } }, "trainer_advance": { "total": 2335.7746622140157, "count": 195364, "self": 13.606915607967949, "children": { "process_trajectory": { "total": 390.70796930601955, "count": 195364, "self": 390.23645298602105, "children": { "RLTrainer._checkpoint": { "total": 0.47151631999849997, "count": 6, "self": 0.47151631999849997 } } }, "_update_policy": { "total": 1931.4597773000282, "count": 1398, "self": 764.1694159230854, "children": { "TorchPPOOptimizer.update": { "total": 1167.2903613769429, "count": 68391, "self": 1167.2903613769429 } } } } } } }, "trainer_threads": { "total": 7.700000423938036e-07, "count": 1, "self": 7.700000423938036e-07 }, "TrainerController._save_models": { "total": 0.0681334370001423, "count": 1, "self": 0.002328538999790908, "children": { "RLTrainer._checkpoint": { "total": 0.06580489800035139, "count": 1, "self": 0.06580489800035139 } } } } } } }