| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.17828094959259033, |
| "min": 0.1721799373626709, |
| "max": 1.4769920110702515, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 5265.7060546875, |
| "min": 5180.63916015625, |
| "max": 44806.03125, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999954.0, |
| "min": 29952.0, |
| "max": 2999954.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999954.0, |
| "min": 29952.0, |
| "max": 2999954.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.7533966898918152, |
| "min": -0.13449205458164215, |
| "max": 0.8544591665267944, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 226.01901245117188, |
| "min": -32.4125862121582, |
| "max": 261.4645080566406, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.002585420850664377, |
| "min": -0.016605578362941742, |
| "max": 0.4719714820384979, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -0.7756262421607971, |
| "min": -4.549928665161133, |
| "max": 111.85723876953125, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.07147376345112987, |
| "min": 0.06372184326637878, |
| "max": 0.07485158303322914, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 1.000632688315818, |
| "min": 0.4676359217426098, |
| "max": 1.0945590881941218, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.015439929482887414, |
| "min": 7.127000181848545e-05, |
| "max": 0.01702970204531171, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.2161590127604238, |
| "min": 0.0009265100236403108, |
| "max": 0.23841582863436392, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.4941280734190472e-06, |
| "min": 1.4941280734190472e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.091779302786666e-05, |
| "min": 2.091779302786666e-05, |
| "max": 0.0039695232768256, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10049800952380951, |
| "min": 0.10049800952380951, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4069721333333332, |
| "min": 1.3962282666666668, |
| "max": 2.7824777333333333, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 5.9751151428571415e-05, |
| "min": 5.9751151428571415e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008365161199999998, |
| "min": 0.0008365161199999998, |
| "max": 0.13232512256, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.005526099819689989, |
| "min": 0.005032707937061787, |
| "max": 0.4690413475036621, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.07736539840698242, |
| "min": 0.07534351944923401, |
| "max": 3.2832894325256348, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 241.43846153846152, |
| "min": 210.74100719424462, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 31387.0, |
| "min": 15984.0, |
| "max": 33090.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7117395186147024, |
| "min": -1.0000000521540642, |
| "max": 1.7897214177463736, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 220.81439790129662, |
| "min": -29.690401628613472, |
| "max": 250.5609984844923, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7117395186147024, |
| "min": -1.0000000521540642, |
| "max": 1.7897214177463736, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 220.81439790129662, |
| "min": -29.690401628613472, |
| "max": 250.5609984844923, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.013703771141969577, |
| "min": 0.01276355956272064, |
| "max": 9.776673128828406, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.7677864773140755, |
| "min": 1.5491279620910063, |
| "max": 156.4267700612545, |
| "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": "1723559769", |
| "python_version": "3.10.1 | packaged by conda-forge | (main, Dec 22 2021, 01:39:36) [GCC 9.4.0]", |
| "command_line_arguments": "/home/aa/miniconda3/envs/rl-unit5/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": "2.1.1+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1723561760" |
| }, |
| "total": 1991.055388856912, |
| "count": 1, |
| "self": 0.1671973499469459, |
| "children": { |
| "run_training.setup": { |
| "total": 0.009938825154677033, |
| "count": 1, |
| "self": 0.009938825154677033 |
| }, |
| "TrainerController.start_learning": { |
| "total": 1990.8782526818104, |
| "count": 1, |
| "self": 2.1196501951199025, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 0.8935073090251535, |
| "count": 1, |
| "self": 0.8935073090251535 |
| }, |
| "TrainerController.advance": { |
| "total": 1987.8339933347888, |
| "count": 194560, |
| "self": 1.9496149611659348, |
| "children": { |
| "env_step": { |
| "total": 1358.5622360771522, |
| "count": 194560, |
| "self": 1210.746600769693, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 146.5065441785846, |
| "count": 194560, |
| "self": 6.1542078596539795, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 140.3523363189306, |
| "count": 187548, |
| "self": 140.3523363189306 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.3090911288745701, |
| "count": 194560, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 1988.1316426536068, |
| "count": 194560, |
| "is_parallel": true, |
| "self": 912.8895388829987, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0007532248273491859, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00022136885672807693, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.000531855970621109, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.000531855970621109 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.015873197931796312, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00015640282072126865, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00013201613910496235, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00013201613910496235 |
| }, |
| "communicator.exchange": { |
| "total": 0.01516228006221354, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.01516228006221354 |
| }, |
| "steps_from_proto": { |
| "total": 0.00042249890975654125, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00011073984205722809, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.00031175906769931316, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.00031175906769931316 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1075.242103770608, |
| "count": 194559, |
| "is_parallel": true, |
| "self": 27.32880406617187, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 17.399412733502686, |
| "count": 194559, |
| "is_parallel": true, |
| "self": 17.399412733502686 |
| }, |
| "communicator.exchange": { |
| "total": 958.0143073941581, |
| "count": 194559, |
| "is_parallel": true, |
| "self": 958.0143073941581 |
| }, |
| "steps_from_proto": { |
| "total": 72.49957957677543, |
| "count": 194559, |
| "is_parallel": true, |
| "self": 16.784605825319886, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 55.714973751455545, |
| "count": 1556472, |
| "is_parallel": true, |
| "self": 55.714973751455545 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 627.3221422964707, |
| "count": 194560, |
| "self": 3.886689353734255, |
| "children": { |
| "process_trajectory": { |
| "total": 133.90792788635008, |
| "count": 194560, |
| "self": 133.6866648425348, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.22126304381527007, |
| "count": 6, |
| "self": 0.22126304381527007 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 489.52752505638637, |
| "count": 1400, |
| "self": 295.3779928740114, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 194.14953218237497, |
| "count": 68394, |
| "self": 194.14953218237497 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 5.068723112344742e-07, |
| "count": 1, |
| "self": 5.068723112344742e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.0311013360042125, |
| "count": 1, |
| "self": 0.0006687080021947622, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.030432628002017736, |
| "count": 1, |
| "self": 0.030432628002017736 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
