{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.44227874279022217, "min": 0.44227874279022217, "max": 1.5689305067062378, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13254.208984375, "min": 13254.208984375, "max": 47595.07421875, "count": 33 }, "Pyramids.Step.mean": { "value": 989904.0, "min": 29952.0, "max": 989904.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989904.0, "min": 29952.0, "max": 989904.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5363729596138, "min": -0.08881853520870209, "max": 0.5582518577575684, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 146.42982482910156, "min": -21.4052677154541, "max": 154.0775146484375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.006174509413540363, "min": -0.013110118918120861, "max": 0.2849091589450836, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.6856410503387451, "min": -3.6183929443359375, "max": 67.52346801757812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0703215702897675, "min": 0.06471818306446582, "max": 0.07411871161769211, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0548235543465125, "min": 0.49775315137632226, "max": 1.0548235543465125, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013745373763231327, "min": 0.00020464200755863343, "max": 0.01424876918439016, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20618060644846992, "min": 0.002864988105820868, "max": 0.2137315377658524, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5386174871600025e-06, "min": 7.5386174871600025e-06, "max": 0.00029515063018788564, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011307926230740004, "min": 0.00011307926230740004, "max": 0.0036354229881923996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10000000000000002, "min": 0.09999999999999998, "max": 0.10000000000000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5000000000000002, "min": 0.7, "max": 1.5000000000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002484685160000001, "min": 0.0002484685160000001, "max": 0.009346598217142855, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0037270277400000013, "min": 0.0037270277400000013, "max": 0.11514054123999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005771522875875235, "min": 0.005771522875875235, "max": 0.25560733675956726, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08657284080982208, "min": 0.0836082175374031, "max": 1.789251446723938, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 367.9620253164557, "min": 338.4457831325301, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29069.0, "min": 15984.0, "max": 33135.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5813847905661487, "min": -1.0000000521540642, "max": 1.6372690349817276, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 124.92939845472574, "min": -28.50300171226263, "max": 137.53059893846512, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5813847905661487, "min": -1.0000000521540642, "max": 1.6372690349817276, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 124.92939845472574, "min": -28.50300171226263, "max": 137.53059893846512, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.022250300517918754, "min": 0.021774323902112275, "max": 6.577478043735027, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.7577737409155816, "min": 1.7577737409155816, "max": 105.23964869976044, "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": "1791215315", "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 Training1 --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": "1791217705" }, "total": 2389.934046936, "count": 1, "self": 0.4794349440003316, "children": { "run_training.setup": { "total": 0.024017061999984435, "count": 1, "self": 0.024017061999984435 }, "TrainerController.start_learning": { "total": 2389.4305949299996, "count": 1, "self": 1.2556504769813728, "children": { "TrainerController._reset_env": { "total": 2.709818240000004, "count": 1, "self": 2.709818240000004 }, "TrainerController.advance": { "total": 2385.330910310018, "count": 63685, "self": 1.3398404460394886, "children": { "env_step": { "total": 1561.9213450640427, "count": 63685, "self": 1411.2567512519986, "children": { "SubprocessEnvManager._take_step": { "total": 149.91700912602846, "count": 63685, "self": 4.481125874029658, "children": { "TorchPolicy.evaluate": { "total": 145.4358832519988, "count": 62553, "self": 145.4358832519988 } } }, "workers": { "total": 0.7475846860156707, "count": 63685, "self": 0.0, "children": { "worker_root": { "total": 2383.2364618841125, "count": 63685, "is_parallel": true, "self": 1085.9060640551147, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023222109998641827, "count": 1, "is_parallel": true, "self": 0.0006385590004356345, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016836519994285482, "count": 8, "is_parallel": true, "self": 0.0016836519994285482 } } }, "UnityEnvironment.step": { "total": 0.09851489399989077, "count": 1, "is_parallel": true, "self": 0.000548538999282755, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00048553400029049953, "count": 1, "is_parallel": true, "self": 0.00048553400029049953 }, "communicator.exchange": { "total": 0.09564666200003558, "count": 1, "is_parallel": true, "self": 0.09564666200003558 }, "steps_from_proto": { "total": 0.001834159000281943, "count": 1, "is_parallel": true, "self": 0.0003417690004425822, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014923899998393608, "count": 8, "is_parallel": true, "self": 0.0014923899998393608 } } } } } } }, "UnityEnvironment.step": { "total": 1297.3303978289978, "count": 63684, "is_parallel": true, "self": 33.55470120302425, "children": { "UnityEnvironment._generate_step_input": { "total": 22.99375589599913, "count": 63684, "is_parallel": true, "self": 22.99375589599913 }, "communicator.exchange": { "total": 1135.528273853024, "count": 63684, "is_parallel": true, "self": 1135.528273853024 }, "steps_from_proto": { "total": 105.25366687695032, "count": 63684, "is_parallel": true, "self": 21.821064803668833, "children": { "_process_rank_one_or_two_observation": { "total": 83.43260207328149, "count": 509472, "is_parallel": true, "self": 83.43260207328149 } } } } } } } } } } }, "trainer_advance": { "total": 822.069724799936, "count": 63685, "self": 2.472995631930644, "children": { "process_trajectory": { "total": 111.316316792012, "count": 63685, "self": 110.95768736701211, "children": { "RLTrainer._checkpoint": { "total": 0.35862942499989003, "count": 2, "self": 0.35862942499989003 } } }, "_update_policy": { "total": 708.2804123759934, "count": 455, "self": 352.65531078997765, "children": { "TorchPPOOptimizer.update": { "total": 355.6251015860157, "count": 30380, "self": 355.6251015860157 } } } } } } }, "trainer_threads": { "total": 9.350005711894482e-07, "count": 1, "self": 9.350005711894482e-07 }, "TrainerController._save_models": { "total": 0.13421496799946908, "count": 1, "self": 0.0016604089987595216, "children": { "RLTrainer._checkpoint": { "total": 0.13255455900070956, "count": 1, "self": 0.13255455900070956 } } } } } } }