{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.14925365149974823, "min": 0.14144892990589142, "max": 1.4910982847213745, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4425.072265625, "min": 4157.466796875, "max": 45233.95703125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999891.0, "min": 29952.0, "max": 2999891.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999891.0, "min": 29952.0, "max": 2999891.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8065932393074036, "min": -0.14577075839042664, "max": 0.8065932393074036, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 241.17138671875, "min": -34.54766845703125, "max": 241.17138671875, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.030329270288348198, "min": -0.017548909410834312, "max": 0.16947656869888306, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.068451881408691, "min": -5.054085731506348, "max": 40.67437744140625, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07271419474065102, "min": 0.06364904063444278, "max": 0.07449865962691893, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0179987263691144, "min": 0.4819773814154872, "max": 1.0716408192238305, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0149526191345926, "min": 8.334409968634264e-05, "max": 0.016406726160009082, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2093366678842964, "min": 0.0009167850965497691, "max": 0.23509123352157663, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5258852056904776e-06, "min": 1.5258852056904776e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1362392879666686e-05, "min": 2.1362392879666686e-05, "max": 0.0037596390467870334, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050859523809527, "min": 0.10050859523809527, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4071203333333338, "min": 1.3897045333333333, "max": 2.6625826333333342, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.080866428571434e-05, "min": 6.080866428571434e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008513213000000007, "min": 0.0008513213000000007, "max": 0.12533597537, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004239528439939022, "min": 0.003976923879235983, "max": 0.2999093234539032, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.05935339629650116, "min": 0.055676937103271484, "max": 2.099365234375, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 226.3111111111111, "min": 226.3111111111111, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30552.0, "min": 15984.0, "max": 32503.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.773688875525086, "min": -1.0000000521540642, "max": 1.773688875525086, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 239.4479981958866, "min": -32.000001668930054, "max": 239.4479981958866, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.773688875525086, "min": -1.0000000521540642, "max": 1.773688875525086, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 239.4479981958866, "min": -32.000001668930054, "max": 239.4479981958866, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.010160676438142589, "min": 0.010160676438142589, "max": 5.95669911429286, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.3716913191492495, "min": 1.1725752901111264, "max": 95.30718582868576, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1785335933", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.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": "1785347599" }, "total": 11665.913807131, "count": 1, "self": 1.140152948002651, "children": { "run_training.setup": { "total": 0.046789825999894674, "count": 1, "self": 0.046789825999894674 }, "TrainerController.start_learning": { "total": 11664.726864356999, "count": 1, "self": 6.729025567990902, "children": { "TrainerController._reset_env": { "total": 3.8231225700001232, "count": 1, "self": 3.8231225700001232 }, "TrainerController.advance": { "total": 11654.056309875008, "count": 194235, "self": 7.294799953713664, "children": { "env_step": { "total": 8512.720195382602, "count": 194235, "self": 8034.20640201952, "children": { "SubprocessEnvManager._take_step": { "total": 474.1865924937547, "count": 194235, "self": 22.009940603504674, "children": { "TorchPolicy.evaluate": { "total": 452.17665189025, "count": 187552, "self": 452.17665189025 } } }, "workers": { "total": 4.327200869327498, "count": 194235, "self": 0.0, "children": { "worker_root": { "total": 11638.654888937708, "count": 194235, "is_parallel": true, "self": 4178.385195535957, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0029098370000610885, "count": 1, "is_parallel": true, "self": 0.0007825570005479676, "children": { "_process_rank_one_or_two_observation": { "total": 0.002127279999513121, "count": 8, "is_parallel": true, "self": 0.002127279999513121 } } }, "UnityEnvironment.step": { "total": 0.06657692099997803, "count": 1, "is_parallel": true, "self": 0.0006916660004208097, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007536299999628682, "count": 1, "is_parallel": true, "self": 0.0007536299999628682 }, "communicator.exchange": { "total": 0.06307394499981456, "count": 1, "is_parallel": true, "self": 0.06307394499981456 }, "steps_from_proto": { "total": 0.0020576799997797934, "count": 1, "is_parallel": true, "self": 0.000417030999869894, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016406489999098994, "count": 8, "is_parallel": true, "self": 0.0016406489999098994 } } } } } } }, "UnityEnvironment.step": { "total": 7460.269693401751, "count": 194234, "is_parallel": true, "self": 144.33288412582624, "children": { "UnityEnvironment._generate_step_input": { "total": 97.28593266392, "count": 194234, "is_parallel": true, "self": 97.28593266392 }, "communicator.exchange": { "total": 6766.264943513277, "count": 194234, "is_parallel": true, "self": 6766.264943513277 }, "steps_from_proto": { "total": 452.3859330987275, "count": 194234, "is_parallel": true, "self": 90.38882167350584, "children": { "_process_rank_one_or_two_observation": { "total": 361.99711142522165, "count": 1553872, "is_parallel": true, "self": 361.99711142522165 } } } } } } } } } } }, "trainer_advance": { "total": 3134.041314538692, "count": 194235, "self": 14.318560169263947, "children": { "process_trajectory": { "total": 460.892764426384, "count": 194235, "self": 460.1573795283848, "children": { "RLTrainer._checkpoint": { "total": 0.7353848979992108, "count": 6, "self": 0.7353848979992108 } } }, "_update_policy": { "total": 2658.829989943044, "count": 1383, "self": 1037.7273986292462, "children": { "TorchPPOOptimizer.update": { "total": 1621.1025913137978, "count": 68418, "self": 1621.1025913137978 } } } } } } }, "trainer_threads": { "total": 1.2309992598602548e-06, "count": 1, "self": 1.2309992598602548e-06 }, "TrainerController._save_models": { "total": 0.1184051130003354, "count": 1, "self": 0.005820735999805038, "children": { "RLTrainer._checkpoint": { "total": 0.11258437700053037, "count": 1, "self": 0.11258437700053037 } } } } } } }