{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.357063889503479, "min": 0.3229082524776459, "max": 1.509750247001648, "count": 36 }, "Pyramids.Policy.Entropy.sum": { "value": 10780.47265625, "min": 9552.91796875, "max": 45799.78515625, "count": 36 }, "Pyramids.Step.mean": { "value": 1079968.0, "min": 29952.0, "max": 1079968.0, "count": 36 }, "Pyramids.Step.sum": { "value": 1079968.0, "min": 29952.0, "max": 1079968.0, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6609543561935425, "min": -0.10109496861696243, "max": 0.717953085899353, "count": 36 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 186.38912963867188, "min": -24.363887786865234, "max": 208.20639038085938, "count": 36 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.010891588404774666, "min": 0.007197369821369648, "max": 0.2011968046426773, "count": 36 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.071427822113037, "min": 2.029658317565918, "max": 48.2872314453125, "count": 36 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07222109096870219, "min": 0.06603155255869439, "max": 0.07331102708468237, "count": 36 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0110952735618306, "min": 0.48308003711582415, "max": 1.0731725864998047, "count": 36 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015217571987462989, "min": 0.0011763430783597794, "max": 0.016209592629494937, "count": 36 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21304600782448185, "min": 0.008739182107374604, "max": 0.24314388944242404, "count": 36 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00019346057122744047, "min": 0.00019346057122744047, "max": 0.00029838354339596195, "count": 36 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0027084479971841665, "min": 0.0020691136102954665, "max": 0.003968965777011433, "count": 36 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.1644868452380952, "min": 0.1644868452380952, "max": 0.19946118095238097, "count": 36 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.302815833333333, "min": 1.3897045333333333, "max": 2.7974840333333337, "count": 36 }, "Pyramids.Policy.Beta.mean": { "value": 0.006452235839285713, "min": 0.006452235839285713, "max": 0.009946171977142856, "count": 36 }, "Pyramids.Policy.Beta.sum": { "value": 0.09033130174999998, "min": 0.06897148288, "max": 0.13230655781, "count": 36 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009454161860048771, "min": 0.008867509663105011, "max": 0.330863893032074, "count": 36 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13235826790332794, "min": 0.12414513528347015, "max": 2.316047191619873, "count": 36 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 311.24, "min": 282.1010101010101, "max": 999.0, "count": 36 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31124.0, "min": 15984.0, "max": 33824.0, "count": 36 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6687519839406013, "min": -1.0000000521540642, "max": 1.7148846021065345, "count": 36 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 166.87519839406013, "min": -32.000001668930054, "max": 178.62299844622612, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6687519839406013, "min": -1.0000000521540642, "max": 1.7148846021065345, "count": 36 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 166.87519839406013, "min": -32.000001668930054, "max": 178.62299844622612, "count": 36 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030253754709265196, "min": 0.026187766512783546, "max": 6.780996962450445, "count": 36 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0253754709265195, "min": 2.665645871522429, "max": 108.49595139920712, "count": 36 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 36 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1703352706", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1703355319" }, "total": 2612.8587016009997, "count": 1, "self": 0.4092223479997301, "children": { "run_training.setup": { "total": 0.050281290000043555, "count": 1, "self": 0.050281290000043555 }, "TrainerController.start_learning": { "total": 2612.399197963, "count": 1, "self": 1.5695541309796681, "children": { "TrainerController._reset_env": { "total": 2.0303926660000116, "count": 1, "self": 2.0303926660000116 }, "TrainerController.advance": { "total": 2608.6680105990204, "count": 69543, "self": 1.6087841420826408, "children": { "env_step": { "total": 1909.9858612029575, "count": 69543, "self": 1761.5860086149628, "children": { "SubprocessEnvManager._take_step": { "total": 147.4138060610336, "count": 69543, "self": 5.328052064052031, "children": { "TorchPolicy.evaluate": { "total": 142.08575399698157, "count": 67774, "self": 142.08575399698157 } } }, "workers": { "total": 0.9860465269611041, "count": 69543, "self": 0.0, "children": { "worker_root": { "total": 2606.303721756051, "count": 69543, "is_parallel": true, "self": 985.1580606050661, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0024070580000170594, "count": 1, "is_parallel": true, "self": 0.0006698310002093422, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017372269998077172, "count": 8, "is_parallel": true, "self": 0.0017372269998077172 } } }, "UnityEnvironment.step": { "total": 0.05330422200006524, "count": 1, "is_parallel": true, "self": 0.0005637429999296728, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005488180000838838, "count": 1, "is_parallel": true, "self": 0.0005488180000838838 }, "communicator.exchange": { "total": 0.050441544000022986, "count": 1, "is_parallel": true, "self": 0.050441544000022986 }, "steps_from_proto": { "total": 0.0017501170000286947, "count": 1, "is_parallel": true, "self": 0.0003662849999273021, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013838320001013926, "count": 8, "is_parallel": true, "self": 0.0013838320001013926 } } } } } } }, "UnityEnvironment.step": { "total": 1621.1456611509848, "count": 69542, "is_parallel": true, "self": 39.028971284001045, "children": { "UnityEnvironment._generate_step_input": { "total": 28.800357806041347, "count": 69542, "is_parallel": true, "self": 28.800357806041347 }, "communicator.exchange": { "total": 1437.5871030989492, "count": 69542, "is_parallel": true, "self": 1437.5871030989492 }, "steps_from_proto": { "total": 115.72922896199316, "count": 69542, "is_parallel": true, "self": 23.7610387710273, "children": { "_process_rank_one_or_two_observation": { "total": 91.96819019096586, "count": 556336, "is_parallel": true, "self": 91.96819019096586 } } } } } } } } } } }, "trainer_advance": { "total": 697.0733652539805, "count": 69543, "self": 3.0122993380165326, "children": { "process_trajectory": { "total": 145.80757599296498, "count": 69543, "self": 145.61025211696483, "children": { "RLTrainer._checkpoint": { "total": 0.197323876000155, "count": 2, "self": 0.197323876000155 } } }, "_update_policy": { "total": 548.2534899229989, "count": 486, "self": 325.14715183296835, "children": { "TorchPPOOptimizer.update": { "total": 223.1063380900306, "count": 24715, "self": 223.1063380900306 } } } } } } }, "trainer_threads": { "total": 1.488000179961091e-06, "count": 1, "self": 1.488000179961091e-06 }, "TrainerController._save_models": { "total": 0.13123907899989717, "count": 1, "self": 0.002002037999773165, "children": { "RLTrainer._checkpoint": { "total": 0.129237041000124, "count": 1, "self": 0.129237041000124 } } } } } } }