{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15071994066238403, "min": 0.14803652465343475, "max": 1.5077581405639648, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4511.9521484375, "min": 4448.20166015625, "max": 45739.3515625, "count": 100 }, "Pyramids.Step.mean": { "value": 2999996.0, "min": 29952.0, "max": 2999996.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999996.0, "min": 29952.0, "max": 2999996.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7497345805168152, "min": -0.09831540286540985, "max": 0.9040558934211731, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 227.16958618164062, "min": -23.694011688232422, "max": 281.161376953125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01719963736832142, "min": -0.02216150425374508, "max": 0.22051340341567993, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.211490154266357, "min": -6.493320941925049, "max": 52.26167678833008, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06911255511872963, "min": 0.06332173679816062, "max": 0.07434474569785698, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9675757716622149, "min": 0.4831407433839036, "max": 1.0876180005337421, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01555315397593554, "min": 3.5719992444883146e-05, "max": 0.016945322503387514, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.21774415566309757, "min": 0.000500079894228364, "max": 0.2541798375508127, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4486709457142882e-06, "min": 1.4486709457142882e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0281393240000036e-05, "min": 2.0281393240000036e-05, "max": 0.0039275934908022, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048285714285717, "min": 0.10048285714285717, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4067600000000002, "min": 1.3962282666666668, "max": 2.7091978000000005, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.823742857142865e-05, "min": 5.823742857142865e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008153240000000011, "min": 0.0008153240000000011, "max": 0.13092886022000003, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.0050439960323274136, "min": 0.0050439960323274136, "max": 0.29111671447753906, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.07061594724655151, "min": 0.07061594724655151, "max": 2.0378170013427734, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 228.7348484848485, "min": 187.25806451612902, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30193.0, "min": 15984.0, "max": 33303.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7404180338844322, "min": -1.0000000521540642, "max": 1.8127179357867975, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 231.47559850662947, "min": -31.99080166220665, "max": 282.7839979827404, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7404180338844322, "min": -1.0000000521540642, "max": 1.8127179357867975, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 231.47559850662947, "min": -31.99080166220665, "max": 282.7839979827404, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012189188642782699, "min": 0.010497263342865782, "max": 5.702630968764424, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.6211620894900989, "min": 1.5237018227489898, "max": 91.24209550023079, "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": "1674299953", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[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 Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1674306611" }, "total": 6657.8570329350005, "count": 1, "self": 0.4925036260010529, "children": { "run_training.setup": { "total": 0.09791167499997755, "count": 1, "self": 0.09791167499997755 }, "TrainerController.start_learning": { "total": 6657.266617633999, "count": 1, "self": 3.765038232880215, "children": { "TrainerController._reset_env": { "total": 10.296631672000103, "count": 1, "self": 10.296631672000103 }, "TrainerController.advance": { "total": 6643.121927204118, "count": 195118, "self": 4.015972863999195, "children": { "env_step": { "total": 4701.885779841092, "count": 195118, "self": 4391.480737600168, "children": { "SubprocessEnvManager._take_step": { "total": 308.0487785609198, "count": 195118, "self": 12.710043596010564, "children": { "TorchPolicy.evaluate": { "total": 295.33873496490924, "count": 187564, "self": 100.17143457984548, "children": { "TorchPolicy.sample_actions": { "total": 195.16730038506375, "count": 187564, "self": 195.16730038506375 } } } } }, "workers": { "total": 2.3562636800040764, "count": 195118, "self": 0.0, "children": { "worker_root": { "total": 6646.502543591864, "count": 195118, "is_parallel": true, "self": 2549.988485565814, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0051770489999398706, "count": 1, "is_parallel": true, "self": 0.0030662109998047526, "children": { "_process_rank_one_or_two_observation": { "total": 0.002110838000135118, "count": 8, "is_parallel": true, "self": 0.002110838000135118 } } }, "UnityEnvironment.step": { "total": 0.04564486200001738, "count": 1, "is_parallel": true, "self": 0.00047227799996107933, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004117720000067493, "count": 1, "is_parallel": true, "self": 0.0004117720000067493 }, "communicator.exchange": { "total": 0.04285201700008656, "count": 1, "is_parallel": true, "self": 0.04285201700008656 }, "steps_from_proto": { "total": 0.0019087949999629927, "count": 1, "is_parallel": true, "self": 0.0006888450000133162, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012199499999496766, "count": 8, "is_parallel": true, "self": 0.0012199499999496766 } } } } } } }, "UnityEnvironment.step": { "total": 4096.51405802605, "count": 195117, "is_parallel": true, "self": 82.86133542811422, "children": { "UnityEnvironment._generate_step_input": { "total": 63.37426435800808, "count": 195117, "is_parallel": true, "self": 63.37426435800808 }, "communicator.exchange": { "total": 3682.352384369153, "count": 195117, "is_parallel": true, "self": 3682.352384369153 }, "steps_from_proto": { "total": 267.92607387077555, "count": 195117, "is_parallel": true, "self": 62.71980149411661, "children": { "_process_rank_one_or_two_observation": { "total": 205.20627237665894, "count": 1560936, "is_parallel": true, "self": 205.20627237665894 } } } } } } } } } } }, "trainer_advance": { "total": 1937.2201744990266, "count": 195118, "self": 7.507366441980366, "children": { "process_trajectory": { "total": 430.03568984804383, "count": 195118, "self": 429.46806292204496, "children": { "RLTrainer._checkpoint": { "total": 0.5676269259988658, "count": 6, "self": 0.5676269259988658 } } }, "_update_policy": { "total": 1499.6771182090024, "count": 1392, "self": 560.5464127579185, "children": { "TorchPPOOptimizer.update": { "total": 939.1307054510839, "count": 68355, "self": 939.1307054510839 } } } } } } }, "trainer_threads": { "total": 1.401000190526247e-06, "count": 1, "self": 1.401000190526247e-06 }, "TrainerController._save_models": { "total": 0.08301912400020228, "count": 1, "self": 0.0014329440000437899, "children": { "RLTrainer._checkpoint": { "total": 0.08158618000015849, "count": 1, "self": 0.08158618000015849 } } } } } } }