{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.16201546788215637, "min": 0.14378134906291962, "max": 1.4954164028167725, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4839.72607421875, "min": 4308.83935546875, "max": 45364.953125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999915.0, "min": 29952.0, "max": 2999915.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999915.0, "min": 29952.0, "max": 2999915.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8459597229957581, "min": -0.11305595934391022, "max": 0.892053484916687, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 248.712158203125, "min": -27.24648666381836, "max": 275.64453125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.02436995320022106, "min": -0.006309435237199068, "max": 0.3307401239871979, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.164766311645508, "min": -1.8991400003433228, "max": 78.38540649414062, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0697072665823812, "min": 0.06449385407280975, "max": 0.0741440906498437, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9759017321533368, "min": 0.47987416985139636, "max": 1.0781322761094108, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014903987739844958, "min": 0.00044547689531077174, "max": 0.017151414264648623, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20865582835782942, "min": 0.004900245848418489, "max": 0.2401197997050807, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4760495080166679e-06, "min": 1.4760495080166679e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.066469311223335e-05, "min": 2.066469311223335e-05, "max": 0.0039826435724521995, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049198333333333, "min": 0.10049198333333333, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4068877666666666, "min": 1.3897045333333333, "max": 2.8275478, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.914913500000005e-05, "min": 5.914913500000005e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008280878900000007, "min": 0.0008280878900000007, "max": 0.13277202522, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0066028498113155365, "min": 0.0063983844593167305, "max": 0.4238572120666504, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09243989735841751, "min": 0.08957738429307938, "max": 2.9670004844665527, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 221.6086956521739, "min": 190.40384615384616, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30582.0, "min": 15984.0, "max": 33796.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7638927401191946, "min": -1.0000000521540642, "max": 1.796489163379001, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 243.41719813644886, "min": -32.000001668930054, "max": 282.04879865050316, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7638927401191946, "min": -1.0000000521540642, "max": 1.796489163379001, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 243.41719813644886, "min": -32.000001668930054, "max": 282.04879865050316, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.015243736900695207, "min": 0.013111674831912508, "max": 8.24758250080049, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1036356922959385, "min": 2.0025807520069066, "max": 131.96132001280785, "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": "1676414364", "python_version": "3.8.16 | packaged by conda-forge | (default, Feb 1 2023, 16:01:55) \n[GCC 11.3.0]", "command_line_arguments": "/home/flahoud/miniconda3/envs/rl/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cu117", "numpy_version": "1.22.0", "end_time_seconds": "1676418947" }, "total": 4582.735295776743, "count": 1, "self": 0.3208195869810879, "children": { "run_training.setup": { "total": 0.027434582822024822, "count": 1, "self": 0.027434582822024822 }, "TrainerController.start_learning": { "total": 4582.38704160694, "count": 1, "self": 3.7716818070039153, "children": { "TrainerController._reset_env": { "total": 2.3813850129954517, "count": 1, "self": 2.3813850129954517 }, "TrainerController.advance": { "total": 4576.1648662909865, "count": 195407, "self": 3.4963156268931925, "children": { "env_step": { "total": 2756.65008532349, "count": 195407, "self": 2462.0574518279172, "children": { "SubprocessEnvManager._take_step": { "total": 292.32465681573376, "count": 195407, "self": 11.435367299709469, "children": { "TorchPolicy.evaluate": { "total": 280.8892895160243, "count": 187544, "self": 92.65028765890747, "children": { "TorchPolicy.sample_actions": { "total": 188.23900185711682, "count": 187544, "self": 188.23900185711682 } } } } }, "workers": { "total": 2.267976679839194, "count": 195407, "self": 0.0, "children": { "worker_root": { "total": 4575.580829973798, "count": 195407, "is_parallel": true, "self": 2348.8864394095726, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016269446350634098, "count": 1, "is_parallel": true, "self": 0.000487353652715683, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011395909823477268, "count": 8, "is_parallel": true, "self": 0.0011395909823477268 } } }, "UnityEnvironment.step": { "total": 0.030379687435925007, "count": 1, "is_parallel": true, "self": 0.00033900700509548187, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026577338576316833, "count": 1, "is_parallel": true, "self": 0.00026577338576316833 }, "communicator.exchange": { "total": 0.02865088591352105, "count": 1, "is_parallel": true, "self": 0.02865088591352105 }, "steps_from_proto": { "total": 0.0011240211315453053, "count": 1, "is_parallel": true, "self": 0.0002810615114867687, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008429596200585365, "count": 8, "is_parallel": true, "self": 0.0008429596200585365 } } } } } } }, "UnityEnvironment.step": { "total": 2226.6943905642256, "count": 195406, "is_parallel": true, "self": 52.37248710403219, "children": { "UnityEnvironment._generate_step_input": { "total": 34.97953980835155, "count": 195406, "is_parallel": true, "self": 34.97953980835155 }, "communicator.exchange": { "total": 1993.1439607026987, "count": 195406, "is_parallel": true, "self": 1993.1439607026987 }, "steps_from_proto": { "total": 146.1984029491432, "count": 195406, "is_parallel": true, "self": 36.983570341486484, "children": { "_process_rank_one_or_two_observation": { "total": 109.21483260765672, "count": 1563248, "is_parallel": true, "self": 109.21483260765672 } } } } } } } } } } }, "trainer_advance": { "total": 1816.0184653406031, "count": 195407, "self": 7.508225677534938, "children": { "process_trajectory": { "total": 379.58097625290975, "count": 195407, "self": 379.1385704888962, "children": { "RLTrainer._checkpoint": { "total": 0.4424057640135288, "count": 6, "self": 0.4424057640135288 } } }, "_update_policy": { "total": 1428.9292634101585, "count": 1390, "self": 489.52672110451385, "children": { "TorchPPOOptimizer.update": { "total": 939.4025423056446, "count": 68388, "self": 939.4025423056446 } } } } } } }, "trainer_threads": { "total": 6.980262696743011e-07, "count": 1, "self": 6.980262696743011e-07 }, "TrainerController._save_models": { "total": 0.06910779792815447, "count": 1, "self": 0.0012263022363185883, "children": { "RLTrainer._checkpoint": { "total": 0.06788149569183588, "count": 1, "self": 0.06788149569183588 } } } } } } }