| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.12754306197166443, |
| "min": 0.11662422120571136, |
| "max": 1.3726329803466797, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 3887.512451171875, |
| "min": 3457.6748046875, |
| "max": 41640.1953125, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999925.0, |
| "min": 29952.0, |
| "max": 2999925.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999925.0, |
| "min": 29952.0, |
| "max": 2999925.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.7287692427635193, |
| "min": -0.09567978233098984, |
| "max": 0.8534398674964905, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 210.61431884765625, |
| "min": -22.96314811706543, |
| "max": 255.0473175048828, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.005433041136711836, |
| "min": -0.006030180491507053, |
| "max": 0.2765362858772278, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 1.5701489448547363, |
| "min": -1.7969938516616821, |
| "max": 66.64524841308594, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06779983309343789, |
| "min": 0.06475485399243466, |
| "max": 0.07524515157949131, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9491976633081304, |
| "min": 0.49750536926633987, |
| "max": 1.1005918777681312, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01498012600159429, |
| "min": 0.0004941923125200734, |
| "max": 0.017754369243654665, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.20972176402232007, |
| "min": 0.006424500062760954, |
| "max": 0.2485611694111653, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.5382137730095256e-06, |
| "min": 1.5382137730095256e-06, |
| "max": 0.00029838354339596195, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.1534992822133358e-05, |
| "min": 2.1534992822133358e-05, |
| "max": 0.0039690292769902664, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10051270476190477, |
| "min": 0.10051270476190477, |
| "max": 0.19946118095238097, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4071778666666668, |
| "min": 1.3962282666666668, |
| "max": 2.752426166666667, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 6.121920571428579e-05, |
| "min": 6.121920571428579e-05, |
| "max": 0.009946171977142856, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.000857068880000001, |
| "min": 0.000857068880000001, |
| "max": 0.13230867236000002, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.0068646869622170925, |
| "min": 0.006309757474809885, |
| "max": 0.4490533769130707, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.09610562026500702, |
| "min": 0.08833660185337067, |
| "max": 3.143373727798462, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 240.8706896551724, |
| "min": 214.5185185185185, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 27941.0, |
| "min": 15984.0, |
| "max": 33229.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.707398268554745, |
| "min": -1.0000000521540642, |
| "max": 1.7833255673794783, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 198.05819915235043, |
| "min": -29.758601620793343, |
| "max": 247.39659851789474, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.707398268554745, |
| "min": -1.0000000521540642, |
| "max": 1.7833255673794783, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 198.05819915235043, |
| "min": -29.758601620793343, |
| "max": 247.39659851789474, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.01727855634052158, |
| "min": 0.015328945569658222, |
| "max": 8.404653816483915, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.004312535500503, |
| "min": 1.9927629240555689, |
| "max": 134.47446106374264, |
| "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": "1691965123", |
| "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": "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": "1691971111" |
| }, |
| "total": 5987.041778091001, |
| "count": 1, |
| "self": 0.3735460990010324, |
| "children": { |
| "run_training.setup": { |
| "total": 0.05995210599985512, |
| "count": 1, |
| "self": 0.05995210599985512 |
| }, |
| "TrainerController.start_learning": { |
| "total": 5986.608279886001, |
| "count": 1, |
| "self": 5.633803349157461, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 1.1828284690000146, |
| "count": 1, |
| "self": 1.1828284690000146 |
| }, |
| "TrainerController.advance": { |
| "total": 5979.689105974843, |
| "count": 195386, |
| "self": 4.949338379999972, |
| "children": { |
| "env_step": { |
| "total": 3840.8783163179874, |
| "count": 195386, |
| "self": 3542.0174232186073, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 295.5673152732111, |
| "count": 195386, |
| "self": 15.938435266602482, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 279.6288800066086, |
| "count": 187570, |
| "self": 279.6288800066086 |
| } |
| } |
| }, |
| "workers": { |
| "total": 3.2935778261689848, |
| "count": 195386, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 5978.108924110849, |
| "count": 195386, |
| "is_parallel": true, |
| "self": 2779.802507998769, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.002529913999751443, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0008389119984713034, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0016910020012801397, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0016910020012801397 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04277477999994517, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00038826800027891295, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00039194200007841573, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00039194200007841573 |
| }, |
| "communicator.exchange": { |
| "total": 0.040589200999875175, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.040589200999875175 |
| }, |
| "steps_from_proto": { |
| "total": 0.001405368999712664, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003431239997553348, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0010622449999573291, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0010622449999573291 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 3198.30641611208, |
| "count": 195385, |
| "is_parallel": true, |
| "self": 70.32096323936139, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 50.6907901759364, |
| "count": 195385, |
| "is_parallel": true, |
| "self": 50.6907901759364 |
| }, |
| "communicator.exchange": { |
| "total": 2851.3586483540403, |
| "count": 195385, |
| "is_parallel": true, |
| "self": 2851.3586483540403 |
| }, |
| "steps_from_proto": { |
| "total": 225.93601434274206, |
| "count": 195385, |
| "is_parallel": true, |
| "self": 51.79661316155443, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 174.13940118118762, |
| "count": 1563080, |
| "is_parallel": true, |
| "self": 174.13940118118762 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 2133.861451276856, |
| "count": 195386, |
| "self": 9.009105705909406, |
| "children": { |
| "process_trajectory": { |
| "total": 334.6258326298939, |
| "count": 195386, |
| "self": 333.98943587389385, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.6363967560000674, |
| "count": 6, |
| "self": 0.6363967560000674 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1790.2265129410525, |
| "count": 1396, |
| "self": 1004.1798568641498, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 786.0466560769028, |
| "count": 68385, |
| "self": 786.0466560769028 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.4899997040629387e-06, |
| "count": 1, |
| "self": 1.4899997040629387e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.10254060300030687, |
| "count": 1, |
| "self": 0.001641583001401159, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.10089901999890571, |
| "count": 1, |
| "self": 0.10089901999890571 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
