{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16684168577194214, "min": 0.16406312584877014, "max": 1.4462881088256836, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5015.92822265625, "min": 4908.7685546875, "max": 43874.59765625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999978.0, "min": 29986.0, "max": 2999978.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999978.0, "min": 29986.0, "max": 2999978.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8669337630271912, "min": -0.18663865327835083, "max": 0.884894847869873, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 261.8139953613281, "min": -44.41999816894531, "max": 273.20947265625, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007690242491662502, "min": -0.006379019934684038, "max": 0.3419843912124634, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.322453260421753, "min": -1.8128371238708496, "max": 81.39228820800781, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06732172209012788, "min": 0.06380117639006735, "max": 0.07498035333184008, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9425041092617903, "min": 0.517075738789321, "max": 1.1247052999776013, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015497177693760023, "min": 0.0002187043390311141, "max": 0.01683522471712957, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21696048771264032, "min": 0.0028431564074044833, "max": 0.23624733213606913, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.548920912297621e-06, "min": 1.548920912297621e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1684892772166695e-05, "min": 2.1684892772166695e-05, "max": 0.003969176276941266, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10051627380952384, "min": 0.10051627380952384, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4072278333333337, "min": 1.3962282666666668, "max": 2.723058733333334, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.157575357142867e-05, "min": 6.157575357142867e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008620605500000013, "min": 0.0008620605500000013, "max": 0.13231356746, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0058973380364477634, "min": 0.005769786424934864, "max": 0.409476101398468, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08256272971630096, "min": 0.08077701181173325, "max": 2.866332769393921, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 209.00746268656715, "min": 199.94520547945206, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28007.0, "min": 16785.0, "max": 33641.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7760656580551346, "min": -0.9997750511392951, "max": 1.8000547760357595, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 237.99279817938805, "min": -31.992801636457443, "max": 281.8433985263109, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7760656580551346, "min": -0.9997750511392951, "max": 1.8000547760357595, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 237.99279817938805, "min": -31.992801636457443, "max": 281.8433985263109, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012773696487498971, "min": 0.012495668347245492, "max": 7.8804929063600655, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.711675329324862, "min": 1.711675329324862, "max": 133.9683794081211, "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": "1780998278", "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": "1781006417" }, "total": 8138.7616654739995, "count": 1, "self": 0.4780764659990382, "children": { "run_training.setup": { "total": 0.025233924000076513, "count": 1, "self": 0.025233924000076513 }, "TrainerController.start_learning": { "total": 8138.258355084001, "count": 1, "self": 4.654055269918899, "children": { "TrainerController._reset_env": { "total": 2.200057547000142, "count": 1, "self": 2.200057547000142 }, "TrainerController.advance": { "total": 8131.3238110190805, "count": 195041, "self": 4.893210342172097, "children": { "env_step": { "total": 6088.810388588772, "count": 195041, "self": 5594.6018975454945, "children": { "SubprocessEnvManager._take_step": { "total": 491.41271962831297, "count": 195041, "self": 14.544152055096674, "children": { "TorchPolicy.evaluate": { "total": 476.8685675732163, "count": 187567, "self": 476.8685675732163 } } }, "workers": { "total": 2.7957714149647472, "count": 195041, "self": 0.0, "children": { "worker_root": { "total": 8120.836763878854, "count": 195041, "is_parallel": true, "self": 2903.301701208781, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001793266999811749, "count": 1, "is_parallel": true, "self": 0.0006401929999810818, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011530739998306672, "count": 8, "is_parallel": true, "self": 0.0011530739998306672 } } }, "UnityEnvironment.step": { "total": 0.05275209499995981, "count": 1, "is_parallel": true, "self": 0.0006126410003162164, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005342639997252263, "count": 1, "is_parallel": true, "self": 0.0005342639997252263 }, "communicator.exchange": { "total": 0.04931695799996305, "count": 1, "is_parallel": true, "self": 0.04931695799996305 }, "steps_from_proto": { "total": 0.0022882319999553147, "count": 1, "is_parallel": true, "self": 0.00044038799933332484, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018478440006219898, "count": 8, "is_parallel": true, "self": 0.0018478440006219898 } } } } } } }, "UnityEnvironment.step": { "total": 5217.535062670073, "count": 195040, "is_parallel": true, "self": 106.13535214637886, "children": { "UnityEnvironment._generate_step_input": { "total": 73.29131723687897, "count": 195040, "is_parallel": true, "self": 73.29131723687897 }, "communicator.exchange": { "total": 4698.5901426044875, "count": 195040, "is_parallel": true, "self": 4698.5901426044875 }, "steps_from_proto": { "total": 339.518250682328, "count": 195040, "is_parallel": true, "self": 71.36108122545329, "children": { "_process_rank_one_or_two_observation": { "total": 268.1571694568747, "count": 1560320, "is_parallel": true, "self": 268.1571694568747 } } } } } } } } } } }, "trainer_advance": { "total": 2037.6202120881362, "count": 195041, "self": 9.133331542264841, "children": { "process_trajectory": { "total": 401.98991164689005, "count": 195041, "self": 401.397807487891, "children": { "RLTrainer._checkpoint": { "total": 0.5921041589990637, "count": 6, "self": 0.5921041589990637 } } }, "_update_policy": { "total": 1626.4969688989813, "count": 1397, "self": 891.3684307339836, "children": { "TorchPPOOptimizer.update": { "total": 735.1285381649977, "count": 68388, "self": 735.1285381649977 } } } } } } }, "trainer_threads": { "total": 9.57999873207882e-07, "count": 1, "self": 9.57999873207882e-07 }, "TrainerController._save_models": { "total": 0.08043029000145907, "count": 1, "self": 0.0011116960013168864, "children": { "RLTrainer._checkpoint": { "total": 0.07931859400014218, "count": 1, "self": 0.07931859400014218 } } } } } } }