| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.36006778478622437, |
| "min": 0.3245562016963959, |
| "max": 1.4868627786636353, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 10669.5283203125, |
| "min": 9669.1787109375, |
| "max": 45105.46875, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989925.0, |
| "min": 29952.0, |
| "max": 989925.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989925.0, |
| "min": 29952.0, |
| "max": 989925.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.5423502922058105, |
| "min": -0.10887411236763, |
| "max": 0.5632745027542114, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 147.519287109375, |
| "min": -26.23866081237793, |
| "max": 157.71685791015625, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.09537006914615631, |
| "min": -0.039356328547000885, |
| "max": 0.2998943626880646, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 25.940658569335938, |
| "min": -10.586852073669434, |
| "max": 71.97464752197266, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.07105379078088195, |
| "min": 0.06614181036090379, |
| "max": 0.0754068587441762, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9947530709323472, |
| "min": 0.5209487875001559, |
| "max": 1.1139361983223353, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.015467581246498626, |
| "min": 0.0011312017725317142, |
| "max": 0.017187433924489452, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.21654613745098078, |
| "min": 0.007918412407722, |
| "max": 0.24062407494285235, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.552318911164287e-06, |
| "min": 7.552318911164287e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010573246475630002, |
| "min": 0.00010573246475630002, |
| "max": 0.0032527859157380997, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10251740714285716, |
| "min": 0.10251740714285716, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4352437000000002, |
| "min": 1.3691136000000002, |
| "max": 2.5273699, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002614889735714287, |
| "min": 0.0002614889735714287, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.003660845630000002, |
| "min": 0.003660845630000002, |
| "max": 0.10844776381000001, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.013922370970249176, |
| "min": 0.013922370970249176, |
| "max": 0.521253228187561, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.19491319358348846, |
| "min": 0.19491319358348846, |
| "max": 3.6487724781036377, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 345.09090909090907, |
| "min": 331.42528735632186, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30368.0, |
| "min": 15984.0, |
| "max": 32477.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.5639681619676677, |
| "min": -1.0000000521540642, |
| "max": 1.5989627718578938, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 137.62919825315475, |
| "min": -32.000001668930054, |
| "max": 137.62919825315475, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.5639681619676677, |
| "min": -1.0000000521540642, |
| "max": 1.5989627718578938, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 137.62919825315475, |
| "min": -32.000001668930054, |
| "max": 137.62919825315475, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.04968073670914402, |
| "min": 0.04968073670914402, |
| "max": 10.231403378769755, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 4.371904830404674, |
| "min": 4.371904830404674, |
| "max": 163.7024540603161, |
| "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": "1743159145", |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", |
| "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": "1.2.0.dev0", |
| "mlagents_envs_version": "1.2.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.6.0+cu124", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1743161464" |
| }, |
| "total": 2319.2635092339997, |
| "count": 1, |
| "self": 0.4768032160000075, |
| "children": { |
| "run_training.setup": { |
| "total": 0.020096942999998646, |
| "count": 1, |
| "self": 0.020096942999998646 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2318.766609075, |
| "count": 1, |
| "self": 1.352054196931931, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.2770004720000543, |
| "count": 1, |
| "self": 2.2770004720000543 |
| }, |
| "TrainerController.advance": { |
| "total": 2315.0510733220676, |
| "count": 63980, |
| "self": 1.4403258740962883, |
| "children": { |
| "env_step": { |
| "total": 1625.385144049005, |
| "count": 63980, |
| "self": 1471.4112774111027, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 153.16666405791693, |
| "count": 63980, |
| "self": 4.596674893936324, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 148.5699891639806, |
| "count": 62569, |
| "self": 148.5699891639806 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.8072025799854146, |
| "count": 63980, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2313.4866075999594, |
| "count": 63980, |
| "is_parallel": true, |
| "self": 955.7925004669232, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.00299857000004522, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000917510999897786, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.002081059000147434, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.002081059000147434 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.047894439000174316, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005108420002670755, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00045361599995885626, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00045361599995885626 |
| }, |
| "communicator.exchange": { |
| "total": 0.04536332299994683, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04536332299994683 |
| }, |
| "steps_from_proto": { |
| "total": 0.0015666580000015529, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003368380002939375, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012298199997076154, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012298199997076154 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1357.6941071330361, |
| "count": 63979, |
| "is_parallel": true, |
| "self": 31.964988219986026, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 22.782211368046774, |
| "count": 63979, |
| "is_parallel": true, |
| "self": 22.782211368046774 |
| }, |
| "communicator.exchange": { |
| "total": 1207.634901503004, |
| "count": 63979, |
| "is_parallel": true, |
| "self": 1207.634901503004 |
| }, |
| "steps_from_proto": { |
| "total": 95.31200604199944, |
| "count": 63979, |
| "is_parallel": true, |
| "self": 19.23121574788911, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 76.08079029411033, |
| "count": 511832, |
| "is_parallel": true, |
| "self": 76.08079029411033 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 688.2256033989665, |
| "count": 63980, |
| "self": 2.636153549961591, |
| "children": { |
| "process_trajectory": { |
| "total": 127.6161246420013, |
| "count": 63980, |
| "self": 127.41792454700158, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.19820009499972002, |
| "count": 2, |
| "self": 0.19820009499972002 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 557.9733252070037, |
| "count": 443, |
| "self": 306.88082107303217, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 251.0925041339715, |
| "count": 22827, |
| "self": 251.0925041339715 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 8.750002962187864e-07, |
| "count": 1, |
| "self": 8.750002962187864e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.0864802090000012, |
| "count": 1, |
| "self": 0.0015289590000975295, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.08495124999990367, |
| "count": 1, |
| "self": 0.08495124999990367 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
