{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.640161395072937, "min": 0.4807933270931244, "max": 1.4716732501983643, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 19286.783203125, "min": 14369.951171875, "max": 44644.6796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989946.0, "min": 29890.0, "max": 989946.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989946.0, "min": 29890.0, "max": 989946.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.17484360933303833, "min": -0.11482644081115723, "max": 0.23208928108215332, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 45.109649658203125, "min": -27.673171997070312, "max": 59.18276596069336, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02535150945186615, "min": 0.017908450216054916, "max": 0.29757678508758545, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.540689468383789, "min": 4.369661808013916, "max": 71.71600341796875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06561526109386855, "min": 0.06547432503756266, "max": 0.07281278392489843, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9842289164080282, "min": 0.48301737353051133, "max": 1.0779182496845867, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012352377294963744, "min": 0.00034532429040889305, "max": 0.012352377294963744, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.18528565942445616, "min": 0.004064235729677842, "max": 0.18528565942445616, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.484177505306671e-06, "min": 7.484177505306671e-06, "max": 0.0002952355730167143, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011226266257960006, "min": 0.00011226266257960006, "max": 0.0030203651932117002, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249469333333333, "min": 0.10249469333333333, "max": 0.1984118571428571, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5374204, "min": 1.3888829999999999, "max": 2.4003192, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002592198640000001, "min": 0.0002592198640000001, "max": 0.009841344528571428, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003888297960000002, "min": 0.003888297960000002, "max": 0.10070815116999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.016525249928236008, "min": 0.016525249928236008, "max": 0.4466330409049988, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.24787874519824982, "min": 0.2341679334640503, "max": 3.1264312267303467, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 610.0, "min": 584.94, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30500.0, "min": 16689.0, "max": 32554.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.9098439665138721, "min": -0.9999871489501768, "max": 0.9098439665138721, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 45.49219832569361, "min": -31.99920167028904, "max": 45.49219832569361, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.9098439665138721, "min": -0.9999871489501768, "max": 0.9098439665138721, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 45.49219832569361, "min": -31.99920167028904, "max": 45.49219832569361, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.10496714407054242, "min": 0.10496714407054242, "max": 8.066202942062827, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.248357203527121, "min": 4.9818434960907325, "max": 137.12545001506805, "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": "1761552985", "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=PyramidsRND --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": "1761555146" }, "total": 2160.402690381, "count": 1, "self": 0.4976508150002701, "children": { "run_training.setup": { "total": 0.025063374999945154, "count": 1, "self": 0.025063374999945154 }, "TrainerController.start_learning": { "total": 2159.879976191, "count": 1, "self": 1.4028838350450314, "children": { "TrainerController._reset_env": { "total": 2.9539895689999867, "count": 1, "self": 2.9539895689999867 }, "TrainerController.advance": { "total": 2155.433540390955, "count": 63298, "self": 1.4026444859546245, "children": { "env_step": { "total": 1502.4476152209886, "count": 63298, "self": 1351.251891049983, "children": { "SubprocessEnvManager._take_step": { "total": 150.36999431998868, "count": 63298, "self": 4.588051269971061, "children": { "TorchPolicy.evaluate": { "total": 145.78194305001762, "count": 62569, "self": 145.78194305001762 } } }, "workers": { "total": 0.8257298510168312, "count": 63298, "self": 0.0, "children": { "worker_root": { "total": 2153.4257412160077, "count": 63298, "is_parallel": true, "self": 917.4115231710075, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005695311000067704, "count": 1, "is_parallel": true, "self": 0.0035132369997654678, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021820740003022365, "count": 8, "is_parallel": true, "self": 0.0021820740003022365 } } }, "UnityEnvironment.step": { "total": 0.05251419599994733, "count": 1, "is_parallel": true, "self": 0.0005360189999237264, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045037899997169006, "count": 1, "is_parallel": true, "self": 0.00045037899997169006 }, "communicator.exchange": { "total": 0.04978511600006641, "count": 1, "is_parallel": true, "self": 0.04978511600006641 }, "steps_from_proto": { "total": 0.001742681999985507, "count": 1, "is_parallel": true, "self": 0.0003451710000490493, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013975109999364577, "count": 8, "is_parallel": true, "self": 0.0013975109999364577 } } } } } } }, "UnityEnvironment.step": { "total": 1236.0142180450002, "count": 63297, "is_parallel": true, "self": 33.595718774955685, "children": { "UnityEnvironment._generate_step_input": { "total": 22.702529982978035, "count": 63297, "is_parallel": true, "self": 22.702529982978035 }, "communicator.exchange": { "total": 1074.2780464450268, "count": 63297, "is_parallel": true, "self": 1074.2780464450268 }, "steps_from_proto": { "total": 105.4379228420396, "count": 63297, "is_parallel": true, "self": 22.105450130014788, "children": { "_process_rank_one_or_two_observation": { "total": 83.33247271202481, "count": 506376, "is_parallel": true, "self": 83.33247271202481 } } } } } } } } } } }, "trainer_advance": { "total": 651.5832806840117, "count": 63298, "self": 2.6212002290307055, "children": { "process_trajectory": { "total": 120.65661502498244, "count": 63298, "self": 120.43210411198231, "children": { "RLTrainer._checkpoint": { "total": 0.22451091300013104, "count": 2, "self": 0.22451091300013104 } } }, "_update_policy": { "total": 528.3054654299985, "count": 440, "self": 292.49906073599834, "children": { "TorchPPOOptimizer.update": { "total": 235.8064046940002, "count": 22860, "self": 235.8064046940002 } } } } } } }, "trainer_threads": { "total": 9.239997780241538e-07, "count": 1, "self": 9.239997780241538e-07 }, "TrainerController._save_models": { "total": 0.08956147200024134, "count": 1, "self": 0.0009580800001458556, "children": { "RLTrainer._checkpoint": { "total": 0.08860339200009548, "count": 1, "self": 0.08860339200009548 } } } } } } }