{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2979374825954437, "min": 0.2979374825954437, "max": 1.353479266166687, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 8923.8232421875, "min": 8923.8232421875, "max": 41059.1484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989907.0, "min": 29952.0, "max": 989907.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6589800715446472, "min": -0.0841200202703476, "max": 0.8067672848701477, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 187.1503448486328, "min": -20.357044219970703, "max": 240.41665649414062, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009829412214457989, "min": -0.0029439840000122786, "max": 0.42868685722351074, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.791553020477295, "min": -0.8125395774841309, "max": 101.59878540039062, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07104022711046995, "min": 0.06149924693874911, "max": 0.0727027391521482, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9945631795465792, "min": 0.5089191740650374, "max": 1.0827229021963956, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015845057009539146, "min": 0.0010237893431240353, "max": 0.016853429538535972, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22183079813354803, "min": 0.014333050803736494, "max": 0.25028837740925763, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4141475286499965e-06, "min": 7.4141475286499965e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010379806540109995, "min": 0.00010379806540109995, "max": 0.0036332239889254, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247134999999999, "min": 0.10247134999999999, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345989, "min": 1.3886848, "max": 2.6110746, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025688786499999987, "min": 0.00025688786499999987, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035964301099999985, "min": 0.0035964301099999985, "max": 0.12112635254000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.013259338214993477, "min": 0.013259338214993477, "max": 0.5204009413719177, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.18563073873519897, "min": 0.18563073873519897, "max": 3.6428065299987793, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 308.3854166666667, "min": 241.23140495867767, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29605.0, "min": 15984.0, "max": 32643.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6499374809985359, "min": -1.0000000521540642, "max": 1.7587685816544147, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 158.39399817585945, "min": -29.930401623249054, "max": 213.73399782180786, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6499374809985359, "min": -1.0000000521540642, "max": 1.7587685816544147, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 158.39399817585945, "min": -29.930401623249054, "max": 213.73399782180786, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0427888337035256, "min": 0.03559912410748956, "max": 10.227979252114892, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.107728035538457, "min": 3.880304527716362, "max": 163.64766803383827, "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": "1677131928", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677134252" }, "total": 2324.021119464, "count": 1, "self": 0.4754692229998909, "children": { "run_training.setup": { "total": 0.10628709000002345, "count": 1, "self": 0.10628709000002345 }, "TrainerController.start_learning": { "total": 2323.439363151, "count": 1, "self": 1.2986382010622037, "children": { "TrainerController._reset_env": { "total": 6.367014501000085, "count": 1, "self": 6.367014501000085 }, "TrainerController.advance": { "total": 2315.6921278049367, "count": 64469, "self": 1.361889323019568, "children": { "env_step": { "total": 1579.1205765900531, "count": 64469, "self": 1470.2945965080198, "children": { "SubprocessEnvManager._take_step": { "total": 108.03527264694912, "count": 64469, "self": 4.512235577886258, "children": { "TorchPolicy.evaluate": { "total": 103.52303706906287, "count": 62565, "self": 35.15671117405691, "children": { "TorchPolicy.sample_actions": { "total": 68.36632589500596, "count": 62565, "self": 68.36632589500596 } } } } }, "workers": { "total": 0.7907074350841867, "count": 64469, "self": 0.0, "children": { "worker_root": { "total": 2318.9195701641047, "count": 64469, "is_parallel": true, "self": 959.2289380551701, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018625559996507945, "count": 1, "is_parallel": true, "self": 0.0006629429999520653, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011996129996987293, "count": 8, "is_parallel": true, "self": 0.0011996129996987293 } } }, "UnityEnvironment.step": { "total": 0.07499156300036702, "count": 1, "is_parallel": true, "self": 0.0005017980001866817, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005546930001401051, "count": 1, "is_parallel": true, "self": 0.0005546930001401051 }, "communicator.exchange": { "total": 0.0721281410001211, "count": 1, "is_parallel": true, "self": 0.0721281410001211 }, "steps_from_proto": { "total": 0.0018069309999191319, "count": 1, "is_parallel": true, "self": 0.00041499399912936497, "children": { "_process_rank_one_or_two_observation": { "total": 0.001391937000789767, "count": 8, "is_parallel": true, "self": 0.001391937000789767 } } } } } } }, "UnityEnvironment.step": { "total": 1359.6906321089346, "count": 64468, "is_parallel": true, "self": 30.82056007289566, "children": { "UnityEnvironment._generate_step_input": { "total": 22.361311980982464, "count": 64468, "is_parallel": true, "self": 22.361311980982464 }, "communicator.exchange": { "total": 1217.177592949031, "count": 64468, "is_parallel": true, "self": 1217.177592949031 }, "steps_from_proto": { "total": 89.33116710602553, "count": 64468, "is_parallel": true, "self": 21.020533225916097, "children": { "_process_rank_one_or_two_observation": { "total": 68.31063388010944, "count": 515744, "is_parallel": true, "self": 68.31063388010944 } } } } } } } } } } }, "trainer_advance": { "total": 735.209661891864, "count": 64469, "self": 2.449281399875872, "children": { "process_trajectory": { "total": 160.50569505398698, "count": 64469, "self": 160.31626434898726, "children": { "RLTrainer._checkpoint": { "total": 0.18943070499972237, "count": 2, "self": 0.18943070499972237 } } }, "_update_policy": { "total": 572.2546854380012, "count": 456, "self": 221.58734638099577, "children": { "TorchPPOOptimizer.update": { "total": 350.6673390570054, "count": 22833, "self": 350.6673390570054 } } } } } } }, "trainer_threads": { "total": 7.630005711689591e-07, "count": 1, "self": 7.630005711689591e-07 }, "TrainerController._save_models": { "total": 0.08158188100060215, "count": 1, "self": 0.0014653690004706732, "children": { "RLTrainer._checkpoint": { "total": 0.08011651200013148, "count": 1, "self": 0.08011651200013148 } } } } } } }