{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.38633057475090027, "min": 0.3684013783931732, "max": 1.4883872270584106, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11676.455078125, "min": 11081.513671875, "max": 45151.71484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989974.0, "min": 29952.0, "max": 989974.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989974.0, "min": 29952.0, "max": 989974.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.37573298811912537, "min": -0.10102500021457672, "max": 0.37573298811912537, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 98.4420394897461, "min": -24.34702491760254, "max": 98.4420394897461, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.06605203449726105, "min": -0.06605203449726105, "max": 0.2123061567544937, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -17.305633544921875, "min": -17.305633544921875, "max": 50.95347595214844, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07098404246720574, "min": 0.06400119966586382, "max": 0.0730096518185726, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9937765945408804, "min": 0.46060455927221194, "max": 1.056165891039806, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016573979315927273, "min": 0.0001880090710513354, "max": 0.016573979315927273, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23203571042298182, "min": 0.0020680997815646896, "max": 0.23203571042298182, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.364497545200002e-06, "min": 7.364497545200002e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010310296563280003, "min": 0.00010310296563280003, "max": 0.0031363727545425, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10245479999999998, "min": 0.10245479999999998, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4343671999999998, "min": 1.3691136000000002, "max": 2.3590406, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025523452000000016, "min": 0.00025523452000000016, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003573283280000002, "min": 0.003573283280000002, "max": 0.10457120425, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007551232818514109, "min": 0.007468819618225098, "max": 0.354964941740036, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1057172566652298, "min": 0.10456347465515137, "max": 2.4847545623779297, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 462.6, "min": 440.578125, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30069.0, "min": 15984.0, "max": 32595.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3835107420499508, "min": -1.0000000521540642, "max": 1.410901514498087, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 89.9281982332468, "min": -32.000001668930054, "max": 91.70859844237566, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3835107420499508, "min": -1.0000000521540642, "max": 1.410901514498087, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 89.9281982332468, "min": -32.000001668930054, "max": 91.70859844237566, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03610453092215511, "min": 0.03610453092215511, "max": 7.589538208208978, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.346794509940082, "min": 2.346794509940082, "max": 121.43261133134365, "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": "1739449203", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739451341" }, "total": 2137.9523061170003, "count": 1, "self": 1.0639530369999193, "children": { "run_training.setup": { "total": 0.02055830400013292, "count": 1, "self": 0.02055830400013292 }, "TrainerController.start_learning": { "total": 2136.867794776, "count": 1, "self": 1.288591347993588, "children": { "TrainerController._reset_env": { "total": 2.265469363999955, "count": 1, "self": 2.265469363999955 }, "TrainerController.advance": { "total": 2133.1921978090063, "count": 63428, "self": 1.3426798010618768, "children": { "env_step": { "total": 1450.994341641965, "count": 63428, "self": 1301.8472810260125, "children": { "SubprocessEnvManager._take_step": { "total": 148.38591302401164, "count": 63428, "self": 4.5587418839581915, "children": { "TorchPolicy.evaluate": { "total": 143.82717114005345, "count": 62575, "self": 143.82717114005345 } } }, "workers": { "total": 0.7611475919409258, "count": 63428, "self": 0.0, "children": { "worker_root": { "total": 2132.0186727369714, "count": 63428, "is_parallel": true, "self": 937.999811418962, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019815120001567266, "count": 1, "is_parallel": true, "self": 0.0006708229998366733, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013106890003200533, "count": 8, "is_parallel": true, "self": 0.0013106890003200533 } } }, "UnityEnvironment.step": { "total": 0.05236106400002427, "count": 1, "is_parallel": true, "self": 0.000522155999988172, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004419790000156354, "count": 1, "is_parallel": true, "self": 0.0004419790000156354 }, "communicator.exchange": { "total": 0.04983720099994571, "count": 1, "is_parallel": true, "self": 0.04983720099994571 }, "steps_from_proto": { "total": 0.001559728000074756, "count": 1, "is_parallel": true, "self": 0.0003399069998977211, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012198210001770349, "count": 8, "is_parallel": true, "self": 0.0012198210001770349 } } } } } } }, "UnityEnvironment.step": { "total": 1194.0188613180094, "count": 63427, "is_parallel": true, "self": 30.60601106594163, "children": { "UnityEnvironment._generate_step_input": { "total": 22.555052580021993, "count": 63427, "is_parallel": true, "self": 22.555052580021993 }, "communicator.exchange": { "total": 1049.3599543820453, "count": 63427, "is_parallel": true, "self": 1049.3599543820453 }, "steps_from_proto": { "total": 91.49784329000045, "count": 63427, "is_parallel": true, "self": 17.839353032147983, "children": { "_process_rank_one_or_two_observation": { "total": 73.65849025785246, "count": 507416, "is_parallel": true, "self": 73.65849025785246 } } } } } } } } } } }, "trainer_advance": { "total": 680.8551763659791, "count": 63428, "self": 2.345073616966147, "children": { "process_trajectory": { "total": 123.58042173400736, "count": 63428, "self": 123.33407779700747, "children": { "RLTrainer._checkpoint": { "total": 0.24634393699989232, "count": 2, "self": 0.24634393699989232 } } }, "_update_policy": { "total": 554.9296810150056, "count": 438, "self": 305.4062659600288, "children": { "TorchPPOOptimizer.update": { "total": 249.5234150549768, "count": 22857, "self": 249.5234150549768 } } } } } } }, "trainer_threads": { "total": 1.0630001270328648e-06, "count": 1, "self": 1.0630001270328648e-06 }, "TrainerController._save_models": { "total": 0.12153519200001028, "count": 1, "self": 0.0020210719999340654, "children": { "RLTrainer._checkpoint": { "total": 0.11951412000007622, "count": 1, "self": 0.11951412000007622 } } } } } } }