{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.2178698778152466, "min": 0.978621244430542, "max": 1.531394362449646, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 36302.265625, "min": 29609.1640625, "max": 46456.37890625, "count": 33 }, "Pyramids.Step.mean": { "value": 989945.0, "min": 29952.0, "max": 989945.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989945.0, "min": 29952.0, "max": 989945.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.09416185319423676, "min": -0.10026509314775467, "max": -0.07534562051296234, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -45.1035270690918, "min": -48.12724304199219, "max": -36.01520538330078, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006924273446202278, "min": 0.006652571260929108, "max": 0.33888018131256104, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.3167269229888916, "min": 3.1998867988586426, "max": 160.62921142578125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06743227906757966, "min": 0.06530650933077896, "max": 0.07187657296773979, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.011484186013695, "min": 0.6368278165203741, "max": 1.078148594516097, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00026463768029013105, "min": 8.607955980854361e-05, "max": 0.009659164084872126, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0039695652043519655, "min": 0.0012185832862744268, "max": 0.08693247676384913, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.4928484146000004e-07, "min": 2.4928484146000004e-07, "max": 9.848108185600001e-06, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 3.7392726219000005e-06, "min": 3.7392726219000005e-06, "max": 0.000125339346608, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249187333333333, "min": 0.10249187333333333, "max": 0.19848106666666665, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373781, "min": 1.4774085000000003, "max": 2.653392, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 3.4669545999999996e-05, "min": 3.4669545999999996e-05, "max": 0.00098496256, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00052004319, "min": 0.00052004319, "max": 0.0125485808, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006172921974211931, "min": 0.006172921974211931, "max": 0.35047006607055664, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09259382635354996, "min": 0.09259382635354996, "max": 3.1542305946350098, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 997.7142857142857, "min": 947.8235294117648, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 27936.0, "min": 15984.0, "max": 32457.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -0.9269714739971927, "min": -1.0000000447034836, "max": -0.7257032734492133, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -25.955201271921396, "min": -31.995601437985897, "max": -16.000000715255737, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -0.9269714739971927, "min": -1.0000000447034836, "max": -0.7257032734492133, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -25.955201271921396, "min": -31.995601437985897, "max": -16.000000715255737, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06642726676156079, "min": 0.06642726676156079, "max": 7.77874572458677, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8599634693237022, "min": 1.8599634693237022, "max": 124.45993159338832, "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": "1679268065", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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 --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": "1679270257" }, "total": 2191.6629659499995, "count": 1, "self": 0.5846875659990474, "children": { "run_training.setup": { "total": 0.10720040500018513, "count": 1, "self": 0.10720040500018513 }, "TrainerController.start_learning": { "total": 2190.9710779790003, "count": 1, "self": 1.3612827802971879, "children": { "TrainerController._reset_env": { "total": 5.8314437640001415, "count": 1, "self": 5.8314437640001415 }, "TrainerController.advance": { "total": 2183.676896880701, "count": 62979, "self": 1.3647283913815045, "children": { "env_step": { "total": 1210.1977025874476, "count": 62979, "self": 1103.0912961345093, "children": { "SubprocessEnvManager._take_step": { "total": 106.31721929490595, "count": 62979, "self": 4.633913444762584, "children": { "TorchPolicy.evaluate": { "total": 101.68330585014337, "count": 62533, "self": 101.68330585014337 } } }, "workers": { "total": 0.7891871580322913, "count": 62979, "self": 0.0, "children": { "worker_root": { "total": 2186.867053809863, "count": 62979, "is_parallel": true, "self": 1190.9609772805125, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001743867000186583, "count": 1, "is_parallel": true, "self": 0.0005617989954771474, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011820680047094356, "count": 8, "is_parallel": true, "self": 0.0011820680047094356 } } }, "UnityEnvironment.step": { "total": 0.04660846600017976, "count": 1, "is_parallel": true, "self": 0.000542361998668639, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045826900168322027, "count": 1, "is_parallel": true, "self": 0.00045826900168322027 }, "communicator.exchange": { "total": 0.04401887800122495, "count": 1, "is_parallel": true, "self": 0.04401887800122495 }, "steps_from_proto": { "total": 0.0015889569986029528, "count": 1, "is_parallel": true, "self": 0.000355634001607541, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012333229969954118, "count": 8, "is_parallel": true, "self": 0.0012333229969954118 } } } } } } }, "UnityEnvironment.step": { "total": 995.9060765293507, "count": 62978, "is_parallel": true, "self": 30.054837589927047, "children": { "UnityEnvironment._generate_step_input": { "total": 21.997584377746534, "count": 62978, "is_parallel": true, "self": 21.997584377746534 }, "communicator.exchange": { "total": 855.7250264272552, "count": 62978, "is_parallel": true, "self": 855.7250264272552 }, "steps_from_proto": { "total": 88.12862813442189, "count": 62978, "is_parallel": true, "self": 18.660616718716483, "children": { "_process_rank_one_or_two_observation": { "total": 69.4680114157054, "count": 503824, "is_parallel": true, "self": 69.4680114157054 } } } } } } } } } } }, "trainer_advance": { "total": 972.1144659018719, "count": 62979, "self": 2.1299416257825214, "children": { "process_trajectory": { "total": 139.69850369111737, "count": 62979, "self": 139.49490435512052, "children": { "RLTrainer._checkpoint": { "total": 0.20359933599684155, "count": 2, "self": 0.20359933599684155 } } }, "_update_policy": { "total": 830.286020584972, "count": 459, "self": 525.5271057420978, "children": { "TorchPPOOptimizer.update": { "total": 304.7589148428742, "count": 38100, "self": 304.7589148428742 } } } } } } }, "trainer_threads": { "total": 9.650029824115336e-07, "count": 1, "self": 9.650029824115336e-07 }, "TrainerController._save_models": { "total": 0.10145358899899293, "count": 1, "self": 0.0016745319990150165, "children": { "RLTrainer._checkpoint": { "total": 0.09977905699997791, "count": 1, "self": 0.09977905699997791 } } } } } } }