| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.16818828880786896, |
| "min": 0.16178002953529358, |
| "max": 1.430572509765625, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 4999.9013671875, |
| "min": 4868.931640625, |
| "max": 43397.84765625, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999991.0, |
| "min": 29952.0, |
| "max": 2999991.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999991.0, |
| "min": 29952.0, |
| "max": 2999991.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.8344693779945374, |
| "min": -0.14294353127479553, |
| "max": 0.8740361928939819, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 250.3408203125, |
| "min": -33.87761688232422, |
| "max": 265.7070007324219, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.01125106867402792, |
| "min": -0.012506031431257725, |
| "max": 0.22256210446357727, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -3.3753206729888916, |
| "min": -3.6121010780334473, |
| "max": 53.63746643066406, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06806405856556466, |
| "min": 0.0625491320556547, |
| "max": 0.07417471195817814, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9528968199179052, |
| "min": 0.5078805635931457, |
| "max": 1.0729400516423746, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.015201756213450898, |
| "min": 0.0004886088187350203, |
| "max": 0.016988613678500155, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.21282458698831258, |
| "min": 0.006351914643555263, |
| "max": 0.2378405914990022, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.4637066549880985e-06, |
| "min": 1.4637066549880985e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.049189316983338e-05, |
| "min": 2.049189316983338e-05, |
| "max": 0.0039689013770329, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10048786904761906, |
| "min": 0.10048786904761906, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4068301666666667, |
| "min": 1.3962282666666668, |
| "max": 2.722967100000001, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 5.8738117857142976e-05, |
| "min": 5.8738117857142976e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008223336500000017, |
| "min": 0.0008223336500000017, |
| "max": 0.13230441329, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.006279570050537586, |
| "min": 0.00597234396263957, |
| "max": 0.3624316155910492, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.08791398257017136, |
| "min": 0.08450140058994293, |
| "max": 2.5370213985443115, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 227.8091603053435, |
| "min": 199.6083916083916, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29843.0, |
| "min": 15984.0, |
| "max": 33840.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.772107679110307, |
| "min": -1.0000000521540642, |
| "max": 1.7864027870493335, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 230.3739982843399, |
| "min": -29.227601654827595, |
| "max": 255.4555985480547, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.772107679110307, |
| "min": -1.0000000521540642, |
| "max": 1.7864027870493335, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 230.3739982843399, |
| "min": -29.227601654827595, |
| "max": 255.4555985480547, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.014698383410555274, |
| "min": 0.01308265817214261, |
| "max": 6.719357218593359, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.9107898433721857, |
| "min": 1.8093951879418455, |
| "max": 107.50971549749374, |
| "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": "1683742599", |
| "python_version": "3.10.6 (main, Mar 10 2023, 10:55:28) [GCC 11.3.0]", |
| "command_line_arguments": "/home/isaac/Documents/RLCourse/venv/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
| "mlagents_version": "0.31.0.dev0", |
| "mlagents_envs_version": "0.31.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "1.11.0+cu102", |
| "numpy_version": "1.21.2", |
| "end_time_seconds": "1683745785" |
| }, |
| "total": 3185.817638646, |
| "count": 1, |
| "self": 0.26887282600000617, |
| "children": { |
| "run_training.setup": { |
| "total": 0.012928571999509586, |
| "count": 1, |
| "self": 0.012928571999509586 |
| }, |
| "TrainerController.start_learning": { |
| "total": 3185.5358372480005, |
| "count": 1, |
| "self": 2.6111109825287713, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.5112144769991573, |
| "count": 1, |
| "self": 2.5112144769991573 |
| }, |
| "TrainerController.advance": { |
| "total": 3180.332816086473, |
| "count": 194522, |
| "self": 2.3703397932786174, |
| "children": { |
| "env_step": { |
| "total": 1992.2784678758599, |
| "count": 194522, |
| "self": 1796.8219581075355, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 193.83634315521704, |
| "count": 194522, |
| "self": 7.267830753949966, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 186.56851240126707, |
| "count": 187543, |
| "self": 186.56851240126707 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.620166613107358, |
| "count": 194522, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 3182.4336364899536, |
| "count": 194522, |
| "is_parallel": true, |
| "self": 1553.5883522329732, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0011676340000121854, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00027836699882755056, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0008892670011846349, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0008892670011846349 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.022584080001252005, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0002769559978332836, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.000229007000598358, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000229007000598358 |
| }, |
| "communicator.exchange": { |
| "total": 0.02052857000126096, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.02052857000126096 |
| }, |
| "steps_from_proto": { |
| "total": 0.0015495470015594037, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00016536700059077702, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013841800009686267, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013841800009686267 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1628.8452842569804, |
| "count": 194521, |
| "is_parallel": true, |
| "self": 52.29713893832559, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 34.096149934106506, |
| "count": 194521, |
| "is_parallel": true, |
| "self": 34.096149934106506 |
| }, |
| "communicator.exchange": { |
| "total": 1405.7416088833506, |
| "count": 194521, |
| "is_parallel": true, |
| "self": 1405.7416088833506 |
| }, |
| "steps_from_proto": { |
| "total": 136.71038650119772, |
| "count": 194521, |
| "is_parallel": true, |
| "self": 26.81926727577593, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 109.89111922542179, |
| "count": 1556168, |
| "is_parallel": true, |
| "self": 109.89111922542179 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1185.6840084173346, |
| "count": 194522, |
| "self": 4.159025371400276, |
| "children": { |
| "process_trajectory": { |
| "total": 193.7674315999684, |
| "count": 194522, |
| "self": 193.32560499196916, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.44182660799924633, |
| "count": 6, |
| "self": 0.44182660799924633 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 987.7575514459659, |
| "count": 1397, |
| "self": 654.7801739759616, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 332.9773774700043, |
| "count": 68313, |
| "self": 332.9773774700043 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 6.099999154685065e-07, |
| "count": 1, |
| "self": 6.099999154685065e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.08069509199958702, |
| "count": 1, |
| "self": 0.0011197109979548259, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.0795753810016322, |
| "count": 1, |
| "self": 0.0795753810016322 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
