{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3414781987667084, "min": 0.3229568600654602, "max": 1.4768258333206177, "count": 35 }, "Pyramids.Policy.Entropy.sum": { "value": 10249.8095703125, "min": 9683.5380859375, "max": 44800.98828125, "count": 35 }, "Pyramids.Step.mean": { "value": 1049999.0, "min": 29978.0, "max": 1049999.0, "count": 35 }, "Pyramids.Step.sum": { "value": 1049999.0, "min": 29978.0, "max": 1049999.0, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6589221954345703, "min": -0.09065193682909012, "max": 0.7241567373275757, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 185.81605529785156, "min": -21.847116470336914, "max": 212.90208435058594, "count": 35 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02746553160250187, "min": -0.0077649326995015144, "max": 0.38338378071784973, "count": 35 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.745279788970947, "min": -2.1425106525421143, "max": 91.2453384399414, "count": 35 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06801666334723831, "min": 0.06657217535811819, "max": 0.0731795493736556, "count": 35 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9522332868613363, "min": 0.4985936847977051, "max": 1.0672017290004685, "count": 35 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014023290805407953, "min": 0.0010239651581319517, "max": 0.015022778502454804, "count": 35 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19632607127571133, "min": 0.010594490329526259, "max": 0.21031889903436726, "count": 35 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019658020590184765, "min": 0.00019658020590184765, "max": 0.00029838354339596195, "count": 35 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.002752122882625867, "min": 0.0020886848037717336, "max": 0.003926618891127066, "count": 35 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1655267238095238, "min": 0.1655267238095238, "max": 0.19946118095238097, "count": 35 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3173741333333333, "min": 1.3962282666666668, "max": 2.7225449333333334, "count": 35 }, "Pyramids.Policy.Beta.mean": { "value": 0.00655611970857143, "min": 0.00655611970857143, "max": 0.009946171977142856, "count": 35 }, "Pyramids.Policy.Beta.sum": { "value": 0.09178567592000002, "min": 0.06962320384, "max": 0.13089640604, "count": 35 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008994421921670437, "min": 0.008994421921670437, "max": 0.4189161956310272, "count": 35 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12592190504074097, "min": 0.12592190504074097, "max": 2.932413339614868, "count": 35 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 312.7171717171717, "min": 260.0357142857143, "max": 999.0, "count": 35 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30959.0, "min": 16777.0, "max": 32316.0, "count": 35 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6854897796803592, "min": -0.9999871489501768, "max": 1.722103554090219, "count": 35 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 165.1779984086752, "min": -30.999601617455482, "max": 192.87559805810452, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6854897796803592, "min": -0.9999871489501768, "max": 1.722103554090219, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 165.1779984086752, "min": -30.999601617455482, "max": 192.87559805810452, "count": 35 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02933361790201161, "min": 0.027352317558490376, "max": 7.996843342833659, "count": 35 }, "Pyramids.Policy.RndReward.sum": { "value": 2.874694554397138, "min": 2.7080981512117432, "max": 135.9463368281722, "count": 35 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 35 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1779148830", "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 --force", "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": "1779151444" }, "total": 2614.020349077, "count": 1, "self": 0.6095254410001871, "children": { "run_training.setup": { "total": 0.024923345999923185, "count": 1, "self": 0.024923345999923185 }, "TrainerController.start_learning": { "total": 2613.38590029, "count": 1, "self": 1.5537437299790327, "children": { "TrainerController._reset_env": { "total": 3.6679993389998344, "count": 1, "self": 3.6679993389998344 }, "TrainerController.advance": { "total": 2608.1613898820206, "count": 67939, "self": 1.5957651680046183, "children": { "env_step": { "total": 1887.567435377964, "count": 67939, "self": 1718.6781491829333, "children": { "SubprocessEnvManager._take_step": { "total": 167.9735204170479, "count": 67939, "self": 5.242191060067853, "children": { "TorchPolicy.evaluate": { "total": 162.73132935698004, "count": 66444, "self": 162.73132935698004 } } }, "workers": { "total": 0.9157657779828696, "count": 67938, "self": 0.0, "children": { "worker_root": { "total": 2607.418744525857, "count": 67938, "is_parallel": true, "self": 1019.0072410697971, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0036665120001089235, "count": 1, "is_parallel": true, "self": 0.0018249680001645174, "children": { "_process_rank_one_or_two_observation": { "total": 0.001841543999944406, "count": 8, "is_parallel": true, "self": 0.001841543999944406 } } }, "UnityEnvironment.step": { "total": 0.04733825799985425, "count": 1, "is_parallel": true, "self": 0.0005757909993917565, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004312840001148288, "count": 1, "is_parallel": true, "self": 0.0004312840001148288 }, "communicator.exchange": { "total": 0.04470358100024896, "count": 1, "is_parallel": true, "self": 0.04470358100024896 }, "steps_from_proto": { "total": 0.0016276020000987046, "count": 1, "is_parallel": true, "self": 0.0003568700003597769, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012707319997389277, "count": 8, "is_parallel": true, "self": 0.0012707319997389277 } } } } } } }, "UnityEnvironment.step": { "total": 1588.41150345606, "count": 67937, "is_parallel": true, "self": 37.4890986830751, "children": { "UnityEnvironment._generate_step_input": { "total": 25.22809416189557, "count": 67937, "is_parallel": true, "self": 25.22809416189557 }, "communicator.exchange": { "total": 1407.0763680820078, "count": 67937, "is_parallel": true, "self": 1407.0763680820078 }, "steps_from_proto": { "total": 118.61794252908157, "count": 67937, "is_parallel": true, "self": 24.62432771082422, "children": { "_process_rank_one_or_two_observation": { "total": 93.99361481825736, "count": 543496, "is_parallel": true, "self": 93.99361481825736 } } } } } } } } } } }, "trainer_advance": { "total": 718.9981893360518, "count": 67938, "self": 3.0223892421531673, "children": { "process_trajectory": { "total": 137.9773634598996, "count": 67938, "self": 137.73225137190002, "children": { "RLTrainer._checkpoint": { "total": 0.24511208799958695, "count": 2, "self": 0.24511208799958695 } } }, "_update_policy": { "total": 577.9984366339991, "count": 479, "self": 320.15141443494895, "children": { "TorchPPOOptimizer.update": { "total": 257.8470221990501, "count": 24201, "self": 257.8470221990501 } } } } } } }, "trainer_threads": { "total": 1.383000380883459e-06, "count": 1, "self": 1.383000380883459e-06 }, "TrainerController._save_models": { "total": 0.0027659560000756755, "count": 1, "self": 2.328000027773669e-05, "children": { "RLTrainer._checkpoint": { "total": 0.002742675999797939, "count": 1, "self": 0.002742675999797939 } } } } } } }