{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3078145384788513, "min": 0.3078145384788513, "max": 1.4291267395019531, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9185.185546875, "min": 9185.185546875, "max": 43353.98828125, "count": 33 }, "Pyramids.Step.mean": { "value": 989936.0, "min": 29952.0, "max": 989936.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989936.0, "min": 29952.0, "max": 989936.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6327440738677979, "min": -0.0769626721739769, "max": 0.641336977481842, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 182.23028564453125, "min": -18.548004150390625, "max": 184.70504760742188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.045068997889757156, "min": -0.024404119700193405, "max": 0.30739131569862366, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 12.97987174987793, "min": -6.881961822509766, "max": 73.77391815185547, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.0681028496629248, "min": 0.06539517313946973, "max": 0.07284634391859798, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.021542744943872, "min": 0.5043614422557903, "max": 1.0241645246986117, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018502246717172155, "min": 0.0009475645138701517, "max": 0.018502246717172155, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2775337007575823, "min": 0.006632951597091062, "max": 0.2775337007575823, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.540657486480001e-06, "min": 7.540657486480001e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011310986229720001, "min": 0.00011310986229720001, "max": 0.003507984830671799, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251352000000001, "min": 0.10251352000000001, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377028000000001, "min": 1.3691136000000002, "max": 2.5723286, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002611006480000001, "min": 0.0002611006480000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003916509720000002, "min": 0.003916509720000002, "max": 0.11695588717999998, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.010580542497336864, "min": 0.010580542497336864, "max": 0.4207768440246582, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1587081402540207, "min": 0.15365663170814514, "max": 2.9454379081726074, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 274.7522935779817, "min": 274.7522935779817, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29948.0, "min": 15984.0, "max": 33254.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6903636210344055, "min": -1.0000000521540642, "max": 1.6903636210344055, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 185.9399983137846, "min": -32.000001668930054, "max": 185.9399983137846, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6903636210344055, "min": -1.0000000521540642, "max": 1.6903636210344055, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 185.9399983137846, "min": -32.000001668930054, "max": 185.9399983137846, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02973850194473264, "min": 0.02973850194473264, "max": 8.60628405585885, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.2712352139205905, "min": 3.2712352139205905, "max": 137.7005448937416, "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": "1705505124", "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": "1705507384" }, "total": 2259.523282015, "count": 1, "self": 0.5415347670000301, "children": { "run_training.setup": { "total": 0.04748449199996685, "count": 1, "self": 0.04748449199996685 }, "TrainerController.start_learning": { "total": 2258.934262756, "count": 1, "self": 1.3114908630082027, "children": { "TrainerController._reset_env": { "total": 2.1329582270000174, "count": 1, "self": 2.1329582270000174 }, "TrainerController.advance": { "total": 2255.4047965659906, "count": 64115, "self": 1.391482413027461, "children": { "env_step": { "total": 1619.3955928389319, "count": 64115, "self": 1494.8820767460015, "children": { "SubprocessEnvManager._take_step": { "total": 123.69977962499888, "count": 64115, "self": 4.577797095066671, "children": { "TorchPolicy.evaluate": { "total": 119.12198252993221, "count": 62569, "self": 119.12198252993221 } } }, "workers": { "total": 0.8137364679314487, "count": 64115, "self": 0.0, "children": { "worker_root": { "total": 2253.9406889580914, "count": 64115, "is_parallel": true, "self": 873.5154466560448, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016248599999926228, "count": 1, "is_parallel": true, "self": 0.0005454860011013807, "children": { "_process_rank_one_or_two_observation": { "total": 0.001079373998891242, "count": 8, "is_parallel": true, "self": 0.001079373998891242 } } }, "UnityEnvironment.step": { "total": 0.0496198179998828, "count": 1, "is_parallel": true, "self": 0.0006033239997123019, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004543009999906644, "count": 1, "is_parallel": true, "self": 0.0004543009999906644 }, "communicator.exchange": { "total": 0.04683249900017472, "count": 1, "is_parallel": true, "self": 0.04683249900017472 }, "steps_from_proto": { "total": 0.0017296940000051109, "count": 1, "is_parallel": true, "self": 0.00036738000062541687, "children": { "_process_rank_one_or_two_observation": { "total": 0.001362313999379694, "count": 8, "is_parallel": true, "self": 0.001362313999379694 } } } } } } }, "UnityEnvironment.step": { "total": 1380.4252423020466, "count": 64114, "is_parallel": true, "self": 34.48437381704798, "children": { "UnityEnvironment._generate_step_input": { "total": 23.48041473800413, "count": 64114, "is_parallel": true, "self": 23.48041473800413 }, "communicator.exchange": { "total": 1225.9452174960356, "count": 64114, "is_parallel": true, "self": 1225.9452174960356 }, "steps_from_proto": { "total": 96.51523625095888, "count": 64114, "is_parallel": true, "self": 19.006206909276898, "children": { "_process_rank_one_or_two_observation": { "total": 77.50902934168198, "count": 512912, "is_parallel": true, "self": 77.50902934168198 } } } } } } } } } } }, "trainer_advance": { "total": 634.6177213140313, "count": 64115, "self": 2.5628645620586212, "children": { "process_trajectory": { "total": 125.52306895997253, "count": 64115, "self": 125.33762654497332, "children": { "RLTrainer._checkpoint": { "total": 0.18544241499921554, "count": 2, "self": 0.18544241499921554 } } }, "_update_policy": { "total": 506.53178779200016, "count": 450, "self": 300.63057313599893, "children": { "TorchPPOOptimizer.update": { "total": 205.90121465600123, "count": 22818, "self": 205.90121465600123 } } } } } } }, "trainer_threads": { "total": 1.0150006346520968e-06, "count": 1, "self": 1.0150006346520968e-06 }, "TrainerController._save_models": { "total": 0.08501608500046132, "count": 1, "self": 0.0015451310000571539, "children": { "RLTrainer._checkpoint": { "total": 0.08347095400040416, "count": 1, "self": 0.08347095400040416 } } } } } } }