| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.5451054573059082, | |
| "min": 0.527115523815155, | |
| "max": 1.499147653579712, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 16239.78125, | |
| "min": 15771.2958984375, | |
| "max": 45478.14453125, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 989909.0, | |
| "min": 29963.0, | |
| "max": 989909.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 989909.0, | |
| "min": 29963.0, | |
| "max": 989909.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.2545397877693176, | |
| "min": -0.10914003849029541, | |
| "max": 0.29674333333969116, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 64.39856719970703, | |
| "min": -26.302749633789062, | |
| "max": 75.96629333496094, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.4100847840309143, | |
| "min": -0.44669562578201294, | |
| "max": 0.4100847840309143, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 103.75144958496094, | |
| "min": -114.35408020019531, | |
| "max": 103.75144958496094, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.07069119227803423, | |
| "min": 0.06367472362702968, | |
| "max": 0.07756737480241806, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.9896766918924793, | |
| "min": 0.5734222664695381, | |
| "max": 1.0584636131408809, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.06451297081574532, | |
| "min": 0.00010443001654728492, | |
| "max": 0.06451297081574532, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.9031815914204344, | |
| "min": 0.0009398701489255642, | |
| "max": 0.9031815914204344, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.2584261519857155e-06, | |
| "min": 7.2584261519857155e-06, | |
| "max": 0.0002948458892180375, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.00010161796612780002, | |
| "min": 0.00010161796612780002, | |
| "max": 0.0028777123407626995, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10241944285714287, | |
| "min": 0.10241944285714287, | |
| "max": 0.19828196250000002, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4338722000000002, | |
| "min": 1.4338722000000002, | |
| "max": 2.3592372999999998, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.0002517023414285715, | |
| "min": 0.0002517023414285715, | |
| "max": 0.009828368053749998, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.003523832780000001, | |
| "min": 0.003523832780000001, | |
| "max": 0.09596780627, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.010628299787640572, | |
| "min": 0.010628299787640572, | |
| "max": 0.36516743898391724, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.1487962007522583, | |
| "min": 0.1487962007522583, | |
| "max": 2.921339511871338, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 578.6734693877551, | |
| "min": 564.6603773584906, | |
| "max": 999.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 28355.0, | |
| "min": 16761.0, | |
| "max": 32743.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.1355428280574935, | |
| "min": -0.9999871489501768, | |
| "max": 1.1355428280574935, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 55.64159857481718, | |
| "min": -31.99920167028904, | |
| "max": 55.96379825472832, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.1355428280574935, | |
| "min": -0.9999871489501768, | |
| "max": 1.1355428280574935, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 55.64159857481718, | |
| "min": -31.99920167028904, | |
| "max": 55.96379825472832, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.06439878850253489, | |
| "min": 0.06416584398676553, | |
| "max": 7.171322130908568, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 3.1555406366242096, | |
| "min": 3.1555406366242096, | |
| "max": 129.08379835635424, | |
| "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": "1698530132", | |
| "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1698532314" | |
| }, | |
| "total": 2181.647669021, | |
| "count": 1, | |
| "self": 0.5822862660002102, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0426315079998858, | |
| "count": 1, | |
| "self": 0.0426315079998858 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 2181.022751247, | |
| "count": 1, | |
| "self": 1.4509973779659049, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 3.3818357719999312, | |
| "count": 1, | |
| "self": 3.3818357719999312 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 2176.110791257034, | |
| "count": 63324, | |
| "self": 1.5293885500773285, | |
| "children": { | |
| "env_step": { | |
| "total": 1541.2200176200156, | |
| "count": 63324, | |
| "self": 1402.110042082996, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 138.1991981090448, | |
| "count": 63324, | |
| "self": 4.745204817058266, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 133.45399329198654, | |
| "count": 62565, | |
| "self": 133.45399329198654 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.9107774279748355, | |
| "count": 63324, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 2176.1641058130435, | |
| "count": 63324, | |
| "is_parallel": true, | |
| "self": 895.2042931380217, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0020296799998504866, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006752809997578879, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0013543990000925987, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0013543990000925987 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.05156365699986054, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.000605891999839514, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0005217099999299535, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005217099999299535 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.048725184999966586, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.048725184999966586 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.001710870000124487, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00039398000012624834, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0013168899999982386, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0013168899999982386 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1280.9598126750218, | |
| "count": 63323, | |
| "is_parallel": true, | |
| "self": 35.60966613691153, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 26.052523264000456, | |
| "count": 63323, | |
| "is_parallel": true, | |
| "self": 26.052523264000456 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1114.828129495034, | |
| "count": 63323, | |
| "is_parallel": true, | |
| "self": 1114.828129495034 | |
| }, | |
| "steps_from_proto": { | |
| "total": 104.46949377907572, | |
| "count": 63323, | |
| "is_parallel": true, | |
| "self": 21.40135566804065, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 83.06813811103507, | |
| "count": 506584, | |
| "is_parallel": true, | |
| "self": 83.06813811103507 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 633.3613850869413, | |
| "count": 63324, | |
| "self": 2.545066446906958, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 123.13808565503791, | |
| "count": 63324, | |
| "self": 122.9782468840383, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.1598387709996132, | |
| "count": 2, | |
| "self": 0.1598387709996132 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 507.6782329849964, | |
| "count": 426, | |
| "self": 301.1761367069705, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 206.50209627802587, | |
| "count": 22803, | |
| "self": 206.50209627802587 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.0769999789772555e-06, | |
| "count": 1, | |
| "self": 1.0769999789772555e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.0791257629998654, | |
| "count": 1, | |
| "self": 0.0013739609998992819, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.07775180199996612, | |
| "count": 1, | |
| "self": 0.07775180199996612 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |