{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34618738293647766, "min": 0.3457709550857544, "max": 1.4440406560897827, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10441.01171875, "min": 10395.2578125, "max": 43806.41796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989882.0, "min": 29952.0, "max": 989882.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6236376762390137, "min": -0.11743897944688797, "max": 0.6469398140907288, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 177.7367401123047, "min": -27.833038330078125, "max": 185.0247802734375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.009863163344562054, "min": -0.01906009018421173, "max": 0.45472222566604614, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.8110015392303467, "min": -4.993743419647217, "max": 107.7691650390625, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0681698954444275, "min": 0.0643494640174876, "max": 0.07380047763154986, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0225484316664126, "min": 0.4894701061492997, "max": 1.033206686841698, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017557969634071923, "min": 0.0013444513743644819, "max": 0.017557969634071923, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.26336954451107886, "min": 0.0158525466944461, "max": 0.26336954451107886, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.600877466406671e-06, "min": 7.600877466406671e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011401316199610007, "min": 0.00011401316199610007, "max": 0.0036328402890532996, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10253359333333334, "min": 0.10253359333333334, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5380039, "min": 1.3886848, "max": 2.6109467000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002631059740000002, "min": 0.0002631059740000002, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003946589610000003, "min": 0.003946589610000003, "max": 0.12111357532999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012519764713943005, "min": 0.012269708327949047, "max": 0.564330518245697, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1877964735031128, "min": 0.1717759221792221, "max": 3.9503135681152344, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 291.62745098039215, "min": 291.62745098039215, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29746.0, "min": 15984.0, "max": 32837.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6691529189839083, "min": -1.0000000521540642, "max": 1.6906288484322656, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 170.25359773635864, "min": -28.548401668667793, "max": 170.25359773635864, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6691529189839083, "min": -1.0000000521540642, "max": 1.6906288484322656, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 170.25359773635864, "min": -28.548401668667793, "max": 170.25359773635864, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03763275888594959, "min": 0.03763275888594959, "max": 11.280651174485683, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8385414063668577, "min": 3.785501716658473, "max": 180.49041879177094, "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": "1755442943", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/envs/mlagents/bin/mlagents-learn /content/ml-agents/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": "1755445237" }, "total": 2294.166160212, "count": 1, "self": 0.8096594919998097, "children": { "run_training.setup": { "total": 0.02408650300003501, "count": 1, "self": 0.02408650300003501 }, "TrainerController.start_learning": { "total": 2293.332414217, "count": 1, "self": 1.3574711280466545, "children": { "TrainerController._reset_env": { "total": 3.0247969859999557, "count": 1, "self": 3.0247969859999557 }, "TrainerController.advance": { "total": 2288.832090262953, "count": 64122, "self": 1.4062142560069333, "children": { "env_step": { "total": 1628.825114446006, "count": 64122, "self": 1478.9579239771074, "children": { "SubprocessEnvManager._take_step": { "total": 149.02812116692405, "count": 64122, "self": 4.605804674935484, "children": { "TorchPolicy.evaluate": { "total": 144.42231649198857, "count": 62562, "self": 144.42231649198857 } } }, "workers": { "total": 0.8390693019745186, "count": 64122, "self": 0.0, "children": { "worker_root": { "total": 2288.1433082559647, "count": 64122, "is_parallel": true, "self": 923.1824547729116, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004943778999972892, "count": 1, "is_parallel": true, "self": 0.0035672829999384703, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013764960000344217, "count": 8, "is_parallel": true, "self": 0.0013764960000344217 } } }, "UnityEnvironment.step": { "total": 0.05044316699991214, "count": 1, "is_parallel": true, "self": 0.000600953999878584, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004822189999913462, "count": 1, "is_parallel": true, "self": 0.0004822189999913462 }, "communicator.exchange": { "total": 0.04760661100010566, "count": 1, "is_parallel": true, "self": 0.04760661100010566 }, "steps_from_proto": { "total": 0.001753382999936548, "count": 1, "is_parallel": true, "self": 0.00039497600005233835, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013584069998842097, "count": 8, "is_parallel": true, "self": 0.0013584069998842097 } } } } } } }, "UnityEnvironment.step": { "total": 1364.9608534830531, "count": 64121, "is_parallel": true, "self": 32.87697501102548, "children": { "UnityEnvironment._generate_step_input": { "total": 23.499995677021957, "count": 64121, "is_parallel": true, "self": 23.499995677021957 }, "communicator.exchange": { "total": 1209.9279744400112, "count": 64121, "is_parallel": true, "self": 1209.9279744400112 }, "steps_from_proto": { "total": 98.6559083549945, "count": 64121, "is_parallel": true, "self": 19.928444967962037, "children": { "_process_rank_one_or_two_observation": { "total": 78.72746338703246, "count": 512968, "is_parallel": true, "self": 78.72746338703246 } } } } } } } } } } }, "trainer_advance": { "total": 658.60076156094, "count": 64122, "self": 2.653152484945849, "children": { "process_trajectory": { "total": 128.64014824899436, "count": 64122, "self": 128.32322765499453, "children": { "RLTrainer._checkpoint": { "total": 0.3169205939998392, "count": 2, "self": 0.3169205939998392 } } }, "_update_policy": { "total": 527.3074608269998, "count": 456, "self": 293.36147203797395, "children": { "TorchPPOOptimizer.update": { "total": 233.94598878902582, "count": 22803, "self": 233.94598878902582 } } } } } } }, "trainer_threads": { "total": 1.1250003808527254e-06, "count": 1, "self": 1.1250003808527254e-06 }, "TrainerController._save_models": { "total": 0.11805471499974374, "count": 1, "self": 0.0018311619996893569, "children": { "RLTrainer._checkpoint": { "total": 0.11622355300005438, "count": 1, "self": 0.11622355300005438 } } } } } } }