{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.45874446630477905, "min": 0.44851788878440857, "max": 1.4769161939620972, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 13872.4326171875, "min": 13398.1259765625, "max": 44803.73046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989958.0, "min": 29952.0, "max": 989958.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989958.0, "min": 29952.0, "max": 989958.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.2777259647846222, "min": -0.24199222028255463, "max": 0.3277578055858612, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 72.76420593261719, "min": -57.35215759277344, "max": 85.87254333496094, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.1051243394613266, "min": 0.0025327526964247227, "max": 0.34381887316703796, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 27.542577743530273, "min": 0.6281226873397827, "max": 82.8603515625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06754946566199779, "min": 0.06483449698931497, "max": 0.07506275184882448, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.013241984929967, "min": 0.5254392629417713, "max": 1.037882516097549, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016018579833649307, "min": 7.507307581179405e-05, "max": 0.016018579833649307, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2402786975047396, "min": 0.0009759499855533226, "max": 0.2402786975047396, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.488457503880003e-06, "min": 7.488457503880003e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011232686255820004, "min": 0.00011232686255820004, "max": 0.0035073881308706994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249612000000001, "min": 0.10249612000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374418, "min": 1.3886848, "max": 2.5691293, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002593623880000002, "min": 0.0002593623880000002, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038904358200000026, "min": 0.0038904358200000026, "max": 0.11693601707000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015379603020846844, "min": 0.015137292444705963, "max": 0.3814837336540222, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.23069404065608978, "min": 0.21192209422588348, "max": 2.6703860759735107, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 524.8474576271186, "min": 524.8474576271186, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30966.0, "min": 15984.0, "max": 34438.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2038881037447413, "min": -1.0000000521540642, "max": 1.2841463932501418, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 71.02939812093973, "min": -30.99940161406994, "max": 71.91219802200794, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2038881037447413, "min": -1.0000000521540642, "max": 1.2841463932501418, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 71.02939812093973, "min": -30.99940161406994, "max": 71.91219802200794, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.08362825711847725, "min": 0.08362825711847725, "max": 7.123258816078305, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.934067169990158, "min": 4.465982984052971, "max": 113.97214105725288, "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": "1787426704", "python_version": "3.10.10 (main, Mar 21 2023, 18:45:11) [GCC 11.2.0]", "command_line_arguments": "/content/miniconda310/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": "1787429222" }, "total": 2517.801681238, "count": 1, "self": 0.6505522670004211, "children": { "run_training.setup": { "total": 0.02797084700000596, "count": 1, "self": 0.02797084700000596 }, "TrainerController.start_learning": { "total": 2517.123158124, "count": 1, "self": 2.2459771220046605, "children": { "TrainerController._reset_env": { "total": 3.626539257000104, "count": 1, "self": 3.626539257000104 }, "TrainerController.advance": { "total": 2511.1958747479944, "count": 63320, "self": 2.2917808118068024, "children": { "env_step": { "total": 1751.9472777650612, "count": 63320, "self": 1600.1742546151656, "children": { "SubprocessEnvManager._take_step": { "total": 150.2321654729394, "count": 63320, "self": 5.120252615985237, "children": { "TorchPolicy.evaluate": { "total": 145.11191285695418, "count": 62567, "self": 145.11191285695418 } } }, "workers": { "total": 1.5408576769561932, "count": 63320, "self": 0.0, "children": { "worker_root": { "total": 2510.767679953983, "count": 63320, "is_parallel": true, "self": 1071.0869706780356, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0050852990000294085, "count": 1, "is_parallel": true, "self": 0.003964489000054527, "children": { "_process_rank_one_or_two_observation": { "total": 0.001120809999974881, "count": 8, "is_parallel": true, "self": 0.001120809999974881 } } }, "UnityEnvironment.step": { "total": 0.04949198500003149, "count": 1, "is_parallel": true, "self": 0.0005257089999304299, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000527639999972962, "count": 1, "is_parallel": true, "self": 0.000527639999972962 }, "communicator.exchange": { "total": 0.04692777600007503, "count": 1, "is_parallel": true, "self": 0.04692777600007503 }, "steps_from_proto": { "total": 0.0015108600000530714, "count": 1, "is_parallel": true, "self": 0.00033523000001878245, "children": { "_process_rank_one_or_two_observation": { "total": 0.001175630000034289, "count": 8, "is_parallel": true, "self": 0.001175630000034289 } } } } } } }, "UnityEnvironment.step": { "total": 1439.6807092759475, "count": 63319, "is_parallel": true, "self": 35.99893850495323, "children": { "UnityEnvironment._generate_step_input": { "total": 26.68208296102557, "count": 63319, "is_parallel": true, "self": 26.68208296102557 }, "communicator.exchange": { "total": 1269.6215408709668, "count": 63319, "is_parallel": true, "self": 1269.6215408709668 }, "steps_from_proto": { "total": 107.37814693900191, "count": 63319, "is_parallel": true, "self": 24.320594801082052, "children": { "_process_rank_one_or_two_observation": { "total": 83.05755213791986, "count": 506552, "is_parallel": true, "self": 83.05755213791986 } } } } } } } } } } }, "trainer_advance": { "total": 756.9568161711261, "count": 63320, "self": 4.36877399910918, "children": { "process_trajectory": { "total": 123.85773558801543, "count": 63320, "self": 123.53165695701568, "children": { "RLTrainer._checkpoint": { "total": 0.32607863099974566, "count": 2, "self": 0.32607863099974566 } } }, "_update_policy": { "total": 628.7303065840015, "count": 443, "self": 244.40921743299305, "children": { "TorchPPOOptimizer.update": { "total": 384.32108915100844, "count": 22815, "self": 384.32108915100844 } } } } } } }, "trainer_threads": { "total": 9.800005500437692e-07, "count": 1, "self": 9.800005500437692e-07 }, "TrainerController._save_models": { "total": 0.054766017000474676, "count": 1, "self": 0.0011842110006909934, "children": { "RLTrainer._checkpoint": { "total": 0.05358180599978368, "count": 1, "self": 0.05358180599978368 } } } } } } }