{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.4965856075286865, "min": 1.4965856075286865, "max": 1.4965856075286865, "count": 1 }, "Pyramids.Policy.Entropy.sum": { "value": 45400.421875, "min": 45400.421875, "max": 45400.421875, "count": 1 }, "Pyramids.Step.mean": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Step.sum": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.08600808680057526, "min": 0.08600808680057526, "max": 0.08600808680057526, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 20.3839168548584, "min": 20.3839168548584, "max": 20.3839168548584, "count": 1 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.25756609439849854, "min": 0.25756609439849854, "max": 0.25756609439849854, "count": 1 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 61.04316711425781, "min": 61.04316711425781, "max": 61.04316711425781, "count": 1 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07188484326766699, "min": 0.07188484326766699, "max": 0.07188484326766699, "count": 1 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.5031939028736689, "min": 0.5031939028736689, "max": 0.5031939028736689, "count": 1 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.006305784135028588, "min": 0.006305784135028588, "max": 0.006305784135028588, "count": 1 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.04414048894520012, "min": 0.04414048894520012, "max": 0.04414048894520012, "count": 1 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00013835433959619048, "min": 0.00013835433959619048, "max": 0.00013835433959619048, "count": 1 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0009684803771733333, "min": 0.0009684803771733333, "max": 0.0009684803771733333, "count": 1 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14611809523809524, "min": 0.14611809523809524, "max": 0.14611809523809524, "count": 1 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.0228266666666668, "min": 1.0228266666666668, "max": 1.0228266666666668, "count": 1 }, "Pyramids.Policy.Beta.mean": { "value": 0.004617197714285715, "min": 0.004617197714285715, "max": 0.004617197714285715, "count": 1 }, "Pyramids.Policy.Beta.sum": { "value": 0.032320384, "min": 0.032320384, "max": 0.032320384, "count": 1 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.42595890164375305, "min": 0.42595890164375305, "max": 0.42595890164375305, "count": 1 }, "Pyramids.Losses.RNDLoss.sum": { "value": 2.9817123413085938, "min": 2.9817123413085938, "max": 2.9817123413085938, "count": 1 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 1 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 15984.0, "min": 15984.0, "max": 15984.0, "count": 1 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.RndReward.mean": { "value": 7.356523561291397, "min": 7.356523561291397, "max": 7.356523561291397, "count": 1 }, "Pyramids.Policy.RndReward.sum": { "value": 117.70437698066235, "min": 117.70437698066235, "max": 117.70437698066235, "count": 1 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1735364162", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ml-agents/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": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1735364234" }, "total": 71.635124787, "count": 1, "self": 0.7070392129999163, "children": { "run_training.setup": { "total": 0.07771508000007543, "count": 1, "self": 0.07771508000007543 }, "TrainerController.start_learning": { "total": 70.850370494, "count": 1, "self": 0.07010627399745317, "children": { "TrainerController._reset_env": { "total": 2.902195200999927, "count": 1, "self": 2.902195200999927 }, "TrainerController.advance": { "total": 67.7836262620026, "count": 1896, "self": 0.07678450200057796, "children": { "env_step": { "total": 48.617134404002854, "count": 1896, "self": 44.059663870005124, "children": { "SubprocessEnvManager._take_step": { "total": 4.517310955999392, "count": 1896, "self": 0.2178728749978518, "children": { "TorchPolicy.evaluate": { "total": 4.29943808100154, "count": 1896, "self": 4.29943808100154 } } }, "workers": { "total": 0.040159577998338136, "count": 1896, "self": 0.0, "children": { "worker_root": { "total": 70.4121905179984, "count": 1896, "is_parallel": true, "self": 31.567749567996202, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0033016339999676347, "count": 1, "is_parallel": true, "self": 0.001163695999821357, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021379380001462778, "count": 8, "is_parallel": true, "self": 0.0021379380001462778 } } }, "UnityEnvironment.step": { "total": 0.06795123500000955, "count": 1, "is_parallel": true, "self": 0.000767558999996254, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005715510000072754, "count": 1, "is_parallel": true, "self": 0.0005715510000072754 }, "communicator.exchange": { "total": 0.06448035300002175, "count": 1, "is_parallel": true, "self": 0.06448035300002175 }, "steps_from_proto": { "total": 0.0021317719999842666, "count": 1, "is_parallel": true, "self": 0.0004157430000759632, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017160289999083034, "count": 8, "is_parallel": true, "self": 0.0017160289999083034 } } } } } } }, "UnityEnvironment.step": { "total": 38.844440950002195, "count": 1895, "is_parallel": true, "self": 1.4583566060009616, "children": { "UnityEnvironment._generate_step_input": { "total": 0.933207287000414, "count": 1895, "is_parallel": true, "self": 0.933207287000414 }, "communicator.exchange": { "total": 32.50677248500028, "count": 1895, "is_parallel": true, "self": 32.50677248500028 }, "steps_from_proto": { "total": 3.946104572000536, "count": 1895, "is_parallel": true, "self": 0.861165769003378, "children": { "_process_rank_one_or_two_observation": { "total": 3.084938802997158, "count": 15160, "is_parallel": true, "self": 3.084938802997158 } } } } } } } } } } }, "trainer_advance": { "total": 19.089707355999167, "count": 1896, "self": 0.09070551899901602, "children": { "process_trajectory": { "total": 4.593256399000097, "count": 1896, "self": 4.593256399000097 }, "_update_policy": { "total": 14.405745438000054, "count": 7, "self": 7.842199120999794, "children": { "TorchPPOOptimizer.update": { "total": 6.5635463170002595, "count": 442, "self": 6.5635463170002595 } } } } } } }, "trainer_threads": { "total": 1.1749999657695298e-06, "count": 1, "self": 1.1749999657695298e-06 }, "TrainerController._save_models": { "total": 0.09444158200005859, "count": 1, "self": 0.0009052660000179458, "children": { "RLTrainer._checkpoint": { "total": 0.09353631600004064, "count": 1, "self": 0.09353631600004064 } } } } } } }