{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.8712995648384094, "min": 0.8712995648384094, "max": 1.5926445722579956, "count": 20 }, "Pyramids.Policy.Entropy.sum": { "value": 13146.16796875, "min": 13146.16796875, "max": 25482.3125, "count": 20 }, "Pyramids.Step.mean": { "value": 299979.0, "min": 14840.0, "max": 299979.0, "count": 20 }, "Pyramids.Step.sum": { "value": 299979.0, "min": 14840.0, "max": 299979.0, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.017820585519075394, "min": -0.44053348898887634, "max": -0.017820585519075394, "count": 20 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -1.1048762798309326, "min": -25.99147605895996, "max": -1.1048762798309326, "count": 20 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.08819270879030228, "min": 0.08819270879030228, "max": 0.5929988026618958, "count": 20 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.467947959899902, "min": 5.467947959899902, "max": 35.57992935180664, "count": 20 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.05108893270759533, "min": 0.04402057221505673, "max": 0.05748463013774849, "count": 20 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.20435573083038133, "min": 0.04733797410153784, "max": 0.20945123440397753, "count": 20 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0023478432096150454, "min": 0.00035561221051870636, "max": 0.05769239012928059, "count": 20 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.009391372838460182, "min": 0.001066836631556119, "max": 0.05769239012928059, "count": 20 }, "Pyramids.Policy.LearningRate.mean": { "value": 6.609847796750003e-06, "min": 6.609847796750003e-06, "max": 0.0002918080027306666, "count": 20 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.643939118700001e-05, "min": 2.643939118700001e-05, "max": 0.0007833430388856668, "count": 20 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10220325000000001, "min": 0.10220325000000001, "max": 0.19726933333333332, "count": 20 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.40881300000000004, "min": 0.19726933333333332, "max": 0.5890486666666667, "count": 20 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002301046750000001, "min": 0.0002301046750000001, "max": 0.009727206399999999, "count": 20 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009204187000000005, "min": 0.0009204187000000005, "max": 0.026115321899999995, "count": 20 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.07838667184114456, "min": 0.07838667184114456, "max": 1.4903794527053833, "count": 20 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.31354668736457825, "min": 0.2308574914932251, "max": 1.4903794527053833, "count": 20 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 956.25, "min": 837.0, "max": 999.0, "count": 20 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 15300.0, "min": 837.0, "max": 16611.0, "count": 20 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.5540133833885192, "min": -1.0000000596046448, "max": -0.259862557053566, "count": 20 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -8.31020075082779, "min": -15.999400943517685, "max": -4.157800912857056, "count": 20 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.5540133833885192, "min": -1.0000000596046448, "max": -0.259862557053566, "count": 20 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -8.31020075082779, "min": -15.999400943517685, "max": -4.157800912857056, "count": 20 }, "Pyramids.Policy.RndReward.mean": { "value": 0.7461959299941857, "min": 0.7461959299941857, "max": 22.325430339032952, "count": 20 }, "Pyramids.Policy.RndReward.sum": { "value": 11.192938949912786, "min": 11.192938949912786, "max": 245.5797337293625, "count": 20 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1694868114", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1694869260" }, "total": 1146.0730957230003, "count": 1, "self": 1.104178900000079, "children": { "run_training.setup": { "total": 0.06282346600028177, "count": 1, "self": 0.06282346600028177 }, "TrainerController.start_learning": { "total": 1144.906093357, "count": 1, "self": 0.6581657149940838, "children": { "TrainerController._reset_env": { "total": 1.2781821590001528, "count": 1, "self": 1.2781821590001528 }, "TrainerController.advance": { "total": 1142.6229799300054, "count": 18969, "self": 0.7275461299946073, "children": { "env_step": { "total": 581.8864162970531, "count": 18969, "self": 515.8263947691839, "children": { "SubprocessEnvManager._take_step": { "total": 65.64571256592808, "count": 18969, "self": 2.1026270129736986, "children": { "TorchPolicy.evaluate": { "total": 63.54308555295438, "count": 18883, "self": 63.54308555295438 } } }, "workers": { "total": 0.41430896194106026, "count": 18969, "self": 0.0, "children": { "worker_root": { "total": 1142.7336867199188, "count": 18969, "is_parallel": true, "self": 676.6361744289961, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002087175000269781, "count": 1, "is_parallel": true, "self": 0.0006519530002151441, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014352220000546367, "count": 8, "is_parallel": true, "self": 0.0014352220000546367 } } }, "UnityEnvironment.step": { "total": 0.060282577000180027, "count": 1, "is_parallel": true, "self": 0.000687024999933783, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036074499985261355, "count": 1, "is_parallel": true, "self": 0.00036074499985261355 }, "communicator.exchange": { "total": 0.05596995700034313, "count": 1, "is_parallel": true, "self": 0.05596995700034313 }, "steps_from_proto": { "total": 0.003264850000050501, "count": 1, "is_parallel": true, "self": 0.00046812099981252686, "children": { "_process_rank_one_or_two_observation": { "total": 0.002796729000237974, "count": 8, "is_parallel": true, "self": 0.002796729000237974 } } } } } } }, "UnityEnvironment.step": { "total": 466.0975122909226, "count": 18968, "is_parallel": true, "self": 13.338931398913246, "children": { "UnityEnvironment._generate_step_input": { "total": 7.4159278610172805, "count": 18968, "is_parallel": true, "self": 7.4159278610172805 }, "communicator.exchange": { "total": 404.24626432492323, "count": 18968, "is_parallel": true, "self": 404.24626432492323 }, "steps_from_proto": { "total": 41.096388706068865, "count": 18968, "is_parallel": true, "self": 8.578528926916078, "children": { "_process_rank_one_or_two_observation": { "total": 32.517859779152786, "count": 151744, "is_parallel": true, "self": 32.517859779152786 } } } } } } } } } } }, "trainer_advance": { "total": 560.0090175029577, "count": 18969, "self": 1.0024876248976398, "children": { "process_trajectory": { "total": 54.63906130305759, "count": 18969, "self": 54.63906130305759 }, "_update_policy": { "total": 504.3674685750025, "count": 58, "self": 127.59769741398623, "children": { "TorchPPOOptimizer.update": { "total": 376.76977116101625, "count": 3414, "self": 376.76977116101625 } } } } } } }, "trainer_threads": { "total": 1.4440001905313693e-06, "count": 1, "self": 1.4440001905313693e-06 }, "TrainerController._save_models": { "total": 0.34676410900010524, "count": 1, "self": 0.009078292000594956, "children": { "RLTrainer._checkpoint": { "total": 0.3376858169995103, "count": 1, "self": 0.3376858169995103 } } } } } } }