{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5710482001304626, "min": 0.5710482001304626, "max": 1.4331490993499756, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16976.12109375, "min": 16976.12109375, "max": 43476.01171875, "count": 33 }, "Pyramids.Step.mean": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989913.0, "min": 29952.0, "max": 989913.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.34657323360443115, "min": -0.10414092242717743, "max": 0.4506351053714752, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 90.80218505859375, "min": -25.09796142578125, "max": 121.67147827148438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.01176738552749157, "min": -0.010416025295853615, "max": 0.5907959938049316, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.083055019378662, "min": -2.739414691925049, "max": 140.01864624023438, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06811974099390496, "min": 0.06506172901146468, "max": 0.07415339000276401, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9536763739146693, "min": 0.4956409907938268, "max": 1.0428620557992392, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014595334841336202, "min": 6.783561328941427e-05, "max": 0.014904428545645821, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20433468777870684, "min": 0.0008818629727623855, "max": 0.21924010492397894, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.260333294207142e-06, "min": 7.260333294207142e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010164466611889999, "min": 0.00010164466611889999, "max": 0.003757495047501699, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10242007857142857, "min": 0.10242007857142857, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4338811, "min": 1.3886848, "max": 2.6524983, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025176584928571433, "min": 0.00025176584928571433, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035247218900000005, "min": 0.0035247218900000005, "max": 0.12526458017, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009680954739451408, "min": 0.009621758945286274, "max": 0.5199336409568787, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13553336262702942, "min": 0.13553336262702942, "max": 3.639535665512085, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 491.7903225806452, "min": 423.3970588235294, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30491.0, "min": 15984.0, "max": 33442.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.2178096500856261, "min": -1.0000000521540642, "max": 1.48557609241845, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 75.50419830530882, "min": -31.993201658129692, "max": 99.53359819203615, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.2178096500856261, "min": -1.0000000521540642, "max": 1.48557609241845, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 75.50419830530882, "min": -31.993201658129692, "max": 99.53359819203615, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04937274310167038, "min": 0.04321805704011471, "max": 11.646772235631943, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.0611100723035634, "min": 2.8956098216876853, "max": 186.34835577011108, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1734604065", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.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": "1734606234" }, "total": 2169.231123259, "count": 1, "self": 0.5463896279998153, "children": { "run_training.setup": { "total": 0.05769434799992723, "count": 1, "self": 0.05769434799992723 }, "TrainerController.start_learning": { "total": 2168.627039283, "count": 1, "self": 1.441332447016066, "children": { "TrainerController._reset_env": { "total": 5.1585161929999686, "count": 1, "self": 5.1585161929999686 }, "TrainerController.advance": { "total": 2161.928573605984, "count": 63538, "self": 1.4139348969424645, "children": { "env_step": { "total": 1463.380284993009, "count": 63538, "self": 1312.498229453129, "children": { "SubprocessEnvManager._take_step": { "total": 150.0343971889397, "count": 63538, "self": 4.596289955877296, "children": { "TorchPolicy.evaluate": { "total": 145.4381072330624, "count": 62554, "self": 145.4381072330624 } } }, "workers": { "total": 0.8476583509402644, "count": 63538, "self": 0.0, "children": { "worker_root": { "total": 2163.6531170970015, "count": 63538, "is_parallel": true, "self": 965.8151964209578, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020353339999701348, "count": 1, "is_parallel": true, "self": 0.0006158880000839417, "children": { "_process_rank_one_or_two_observation": { "total": 0.001419445999886193, "count": 8, "is_parallel": true, "self": 0.001419445999886193 } } }, "UnityEnvironment.step": { "total": 0.0464343190000136, "count": 1, "is_parallel": true, "self": 0.0006316520000382297, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045648399998299283, "count": 1, "is_parallel": true, "self": 0.00045648399998299283 }, "communicator.exchange": { "total": 0.043727874999945016, "count": 1, "is_parallel": true, "self": 0.043727874999945016 }, "steps_from_proto": { "total": 0.0016183080000473637, "count": 1, "is_parallel": true, "self": 0.000334670999905029, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012836370001423347, "count": 8, "is_parallel": true, "self": 0.0012836370001423347 } } } } } } }, "UnityEnvironment.step": { "total": 1197.8379206760437, "count": 63537, "is_parallel": true, "self": 32.93414274898305, "children": { "UnityEnvironment._generate_step_input": { "total": 22.850667792019294, "count": 63537, "is_parallel": true, "self": 22.850667792019294 }, "communicator.exchange": { "total": 1047.1493988040347, "count": 63537, "is_parallel": true, "self": 1047.1493988040347 }, "steps_from_proto": { "total": 94.90371133100678, "count": 63537, "is_parallel": true, "self": 18.953054925030415, "children": { "_process_rank_one_or_two_observation": { "total": 75.95065640597636, "count": 508296, "is_parallel": true, "self": 75.95065640597636 } } } } } } } } } } }, "trainer_advance": { "total": 697.1343537160328, "count": 63538, "self": 2.6787600809755077, "children": { "process_trajectory": { "total": 131.05217994705527, "count": 63538, "self": 130.79689630405528, "children": { "RLTrainer._checkpoint": { "total": 0.2552836429999843, "count": 2, "self": 0.2552836429999843 } } }, "_update_policy": { "total": 563.403413688002, "count": 451, "self": 315.68802176300744, "children": { "TorchPPOOptimizer.update": { "total": 247.7153919249946, "count": 22773, "self": 247.7153919249946 } } } } } } }, "trainer_threads": { "total": 9.689997568784747e-07, "count": 1, "self": 9.689997568784747e-07 }, "TrainerController._save_models": { "total": 0.0986160679999557, "count": 1, "self": 0.001947292999830097, "children": { "RLTrainer._checkpoint": { "total": 0.0966687750001256, "count": 1, "self": 0.0966687750001256 } } } } } } }