{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.37524667382240295, "min": 0.37524667382240295, "max": 1.4586886167526245, "count": 35 }, "Pyramids.Policy.Entropy.sum": { "value": 11257.400390625, "min": 11257.400390625, "max": 44250.77734375, "count": 35 }, "Pyramids.Step.mean": { "value": 1049999.0, "min": 29952.0, "max": 1049999.0, "count": 35 }, "Pyramids.Step.sum": { "value": 1049999.0, "min": 29952.0, "max": 1049999.0, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6400670409202576, "min": -0.08483114093542099, "max": 0.6400670409202576, "count": 35 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 183.69923400878906, "min": -20.444305419921875, "max": 183.69923400878906, "count": 35 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.031259454786777496, "min": -0.0008892748737707734, "max": 0.4194074273109436, "count": 35 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 8.971463203430176, "min": -0.23654711246490479, "max": 99.3995590209961, "count": 35 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06786058484111143, "min": 0.0656173204791801, "max": 0.07370817839788893, "count": 35 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9500481877755601, "min": 0.5102428090656591, "max": 1.0704549145508175, "count": 35 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0159418177389845, "min": 0.0010804988183737588, "max": 0.01688079499799438, "count": 35 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.223185448345783, "min": 0.013896404247797077, "max": 0.2363311299719213, "count": 35 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019648987736052857, "min": 0.00019648987736052857, "max": 0.00029838354339596195, "count": 35 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0027508582830474, "min": 0.0020886848037717336, "max": 0.003969548276817266, "count": 35 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.16549661428571433, "min": 0.16549661428571433, "max": 0.19946118095238097, "count": 35 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.3169526000000005, "min": 1.3962282666666668, "max": 2.7231827333333336, "count": 35 }, "Pyramids.Policy.Beta.mean": { "value": 0.0065531117671428565, "min": 0.0065531117671428565, "max": 0.009946171977142856, "count": 35 }, "Pyramids.Policy.Beta.sum": { "value": 0.09174356473999999, "min": 0.06962320384, "max": 0.13232595506, "count": 35 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010311662219464779, "min": 0.009269430302083492, "max": 0.4588625133037567, "count": 35 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.14436326920986176, "min": 0.12977202236652374, "max": 3.2120375633239746, "count": 35 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 313.64761904761906, "min": 313.64761904761906, "max": 999.0, "count": 35 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32933.0, "min": 15984.0, "max": 33115.0, "count": 35 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6465249854641466, "min": -1.0000000521540642, "max": 1.6465249854641466, "count": 35 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 171.23859848827124, "min": -29.481201604008675, "max": 171.23859848827124, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6465249854641466, "min": -1.0000000521540642, "max": 1.6465249854641466, "count": 35 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 171.23859848827124, "min": -29.481201604008675, "max": 171.23859848827124, "count": 35 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03414485929645777, "min": 0.03414485929645777, "max": 10.060727511532605, "count": 35 }, "Pyramids.Policy.RndReward.sum": { "value": 3.551065366831608, "min": 2.835761127586011, "max": 160.97164018452168, "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": "1726547253", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1726550557" }, "total": 3303.84754587, "count": 1, "self": 0.6367979179999566, "children": { "run_training.setup": { "total": 0.07237858700000288, "count": 1, "self": 0.07237858700000288 }, "TrainerController.start_learning": { "total": 3303.138369365, "count": 1, "self": 2.3282299389670698, "children": { "TrainerController._reset_env": { "total": 3.630114555999995, "count": 1, "self": 3.630114555999995 }, "TrainerController.advance": { "total": 3296.981867628033, "count": 68418, "self": 2.5556096539758073, "children": { "env_step": { "total": 2170.2820600560367, "count": 68418, "self": 1999.827129005098, "children": { "SubprocessEnvManager._take_step": { "total": 169.04672429392937, "count": 68418, "self": 6.989342314978586, "children": { "TorchPolicy.evaluate": { "total": 162.0573819789508, "count": 67048, "self": 162.0573819789508 } } }, "workers": { "total": 1.4082067570094239, "count": 68418, "self": 0.0, "children": { "worker_root": { "total": 3294.3482079840064, "count": 68418, "is_parallel": true, "self": 1475.957629147993, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0035415860000114208, "count": 1, "is_parallel": true, "self": 0.0008068950000108543, "children": { "_process_rank_one_or_two_observation": { "total": 0.0027346910000005664, "count": 8, "is_parallel": true, "self": 0.0027346910000005664 } } }, "UnityEnvironment.step": { "total": 0.06312188399999741, "count": 1, "is_parallel": true, "self": 0.0007851679999930639, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005291810000187525, "count": 1, "is_parallel": true, "self": 0.0005291810000187525 }, "communicator.exchange": { "total": 0.05974982699999032, "count": 1, "is_parallel": true, "self": 0.05974982699999032 }, "steps_from_proto": { "total": 0.002057707999995273, "count": 1, "is_parallel": true, "self": 0.00041691800004173274, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016407899999535402, "count": 8, "is_parallel": true, "self": 0.0016407899999535402 } } } } } } }, "UnityEnvironment.step": { "total": 1818.3905788360134, "count": 68417, "is_parallel": true, "self": 49.56606561310923, "children": { "UnityEnvironment._generate_step_input": { "total": 30.184317901958224, "count": 68417, "is_parallel": true, "self": 30.184317901958224 }, "communicator.exchange": { "total": 1604.4887814959748, "count": 68417, "is_parallel": true, "self": 1604.4887814959748 }, "steps_from_proto": { "total": 134.15141382497134, "count": 68417, "is_parallel": true, "self": 28.78362320804098, "children": { "_process_rank_one_or_two_observation": { "total": 105.36779061693036, "count": 547336, "is_parallel": true, "self": 105.36779061693036 } } } } } } } } } } }, "trainer_advance": { "total": 1124.1441979180202, "count": 68418, "self": 4.379820644990332, "children": { "process_trajectory": { "total": 171.66725188202966, "count": 68418, "self": 171.37654297502948, "children": { "RLTrainer._checkpoint": { "total": 0.29070890700018026, "count": 2, "self": 0.29070890700018026 } } }, "_update_policy": { "total": 948.0971253910001, "count": 486, "self": 385.04267651704606, "children": { "TorchPPOOptimizer.update": { "total": 563.054448873954, "count": 24395, "self": 563.054448873954 } } } } } } }, "trainer_threads": { "total": 1.981999957934022e-06, "count": 1, "self": 1.981999957934022e-06 }, "TrainerController._save_models": { "total": 0.19815526000002137, "count": 1, "self": 0.002664701999947283, "children": { "RLTrainer._checkpoint": { "total": 0.1954905580000741, "count": 1, "self": 0.1954905580000741 } } } } } } }