{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3703201115131378, "min": 0.35452356934547424, "max": 1.4542715549468994, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 11008.8759765625, "min": 10635.70703125, "max": 44116.78125, "count": 50 }, "Pyramids.Step.mean": { "value": 1499885.0, "min": 29952.0, "max": 1499885.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499885.0, "min": 29952.0, "max": 1499885.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.1285243034362793, "min": -0.01922598108649254, "max": 0.1582946479320526, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 34.44451141357422, "min": -4.6142354011535645, "max": 42.73955535888672, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019948352128267288, "min": -0.025807682424783707, "max": 0.33405327796936035, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.346158504486084, "min": -6.632574558258057, "max": 79.17062377929688, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06691170591392535, "min": 0.06592669638751938, "max": 0.07260194229938907, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.936763882794955, "min": 0.5082135960957235, "max": 1.0513253781900858, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01054493207456129, "min": 2.2279850425345546e-05, "max": 0.010781968029797489, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.14762904904385804, "min": 0.00031191790595483767, "max": 0.15094755241716484, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.117427532319047e-06, "min": 3.117427532319047e-06, "max": 0.00029676708679192377, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.364398545246666e-05, "min": 4.364398545246666e-05, "max": 0.0038220173259942663, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10103910952380953, "min": 0.10103910952380953, "max": 0.19892236190476192, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4145475333333333, "min": 1.3924565333333334, "max": 2.6740057333333334, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.00011380704142857139, "min": 0.00011380704142857139, "max": 0.009892343954285714, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.0015932985799999996, "min": 0.0015932985799999996, "max": 0.12741317276, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010345285758376122, "min": 0.007989278994500637, "max": 0.4219653904438019, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1448339968919754, "min": 0.11184991151094437, "max": 2.9537577629089355, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 409.8918918918919, "min": 366.6666666666667, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30332.0, "min": 15984.0, "max": 32731.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4008594395945202, "min": -1.0000000521540642, "max": 1.5307358736411119, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 103.66359852999449, "min": -31.994401663541794, "max": 119.39739814400673, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4008594395945202, "min": -1.0000000521540642, "max": 1.5307358736411119, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 103.66359852999449, "min": -31.994401663541794, "max": 119.39739814400673, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.045321977208053844, "min": 0.04165389548348358, "max": 9.579604600556195, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 3.3538263133959845, "min": 2.5207604663373786, "max": 153.27367360889912, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687953182", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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-Training2 --no-graphics", "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": "1687956678" }, "total": 3496.7904946909994, "count": 1, "self": 0.9831543609993787, "children": { "run_training.setup": { "total": 0.05832427199993617, "count": 1, "self": 0.05832427199993617 }, "TrainerController.start_learning": { "total": 3495.749016058, "count": 1, "self": 1.9014641101161942, "children": { "TrainerController._reset_env": { "total": 5.197509943000114, "count": 1, "self": 5.197509943000114 }, "TrainerController.advance": { "total": 3488.564108342883, "count": 95604, "self": 2.040290437816111, "children": { "env_step": { "total": 2255.523786915128, "count": 95604, "self": 2094.2579164371227, "children": { "SubprocessEnvManager._take_step": { "total": 160.15160448502434, "count": 95604, "self": 6.8386067830890624, "children": { "TorchPolicy.evaluate": { "total": 153.31299770193527, "count": 93790, "self": 153.31299770193527 } } }, "workers": { "total": 1.1142659929805632, "count": 95604, "self": 0.0, "children": { "worker_root": { "total": 3488.526439698874, "count": 95604, "is_parallel": true, "self": 1555.5334045939687, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002648281000119823, "count": 1, "is_parallel": true, "self": 0.0007826089997706731, "children": { "_process_rank_one_or_two_observation": { "total": 0.00186567200034915, "count": 8, "is_parallel": true, "self": 0.00186567200034915 } } }, "UnityEnvironment.step": { "total": 0.06963693400007287, "count": 1, "is_parallel": true, "self": 0.0006196930000896828, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004840269998567237, "count": 1, "is_parallel": true, "self": 0.0004840269998567237 }, "communicator.exchange": { "total": 0.06640158100003646, "count": 1, "is_parallel": true, "self": 0.06640158100003646 }, "steps_from_proto": { "total": 0.0021316330000900052, "count": 1, "is_parallel": true, "self": 0.00045797500047228823, "children": { "_process_rank_one_or_two_observation": { "total": 0.001673657999617717, "count": 8, "is_parallel": true, "self": 0.001673657999617717 } } } } } } }, "UnityEnvironment.step": { "total": 1932.9930351049054, "count": 95603, "is_parallel": true, "self": 49.06919217066002, "children": { "UnityEnvironment._generate_step_input": { "total": 33.5711207769682, "count": 95603, "is_parallel": true, "self": 33.5711207769682 }, "communicator.exchange": { "total": 1700.802364199056, "count": 95603, "is_parallel": true, "self": 1700.802364199056 }, "steps_from_proto": { "total": 149.55035795822118, "count": 95603, "is_parallel": true, "self": 29.306729887633082, "children": { "_process_rank_one_or_two_observation": { "total": 120.2436280705881, "count": 764824, "is_parallel": true, "self": 120.2436280705881 } } } } } } } } } } }, "trainer_advance": { "total": 1231.0000309899392, "count": 95604, "self": 3.752872079964618, "children": { "process_trajectory": { "total": 158.88900770196938, "count": 95604, "self": 158.62577242696875, "children": { "RLTrainer._checkpoint": { "total": 0.2632352750006248, "count": 3, "self": 0.2632352750006248 } } }, "_update_policy": { "total": 1068.3581512080052, "count": 693, "self": 664.8701356629922, "children": { "TorchPPOOptimizer.update": { "total": 403.488015545013, "count": 45516, "self": 403.488015545013 } } } } } } }, "trainer_threads": { "total": 8.080005500232801e-07, "count": 1, "self": 8.080005500232801e-07 }, "TrainerController._save_models": { "total": 0.0859328540000206, "count": 1, "self": 0.001130849000219314, "children": { "RLTrainer._checkpoint": { "total": 0.08480200499980128, "count": 1, "self": 0.08480200499980128 } } } } } } }