| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.45454397797584534, |
| "min": 0.45454397797584534, |
| "max": 1.453148365020752, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 13665.41015625, |
| "min": 13665.41015625, |
| "max": 44082.70703125, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989968.0, |
| "min": 29952.0, |
| "max": 989968.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989968.0, |
| "min": 29952.0, |
| "max": 989968.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.357928067445755, |
| "min": -0.09650328010320663, |
| "max": 0.38244059681892395, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 95.5667953491211, |
| "min": -23.25728988647461, |
| "max": 100.96431732177734, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.023215750232338905, |
| "min": -0.023215750232338905, |
| "max": 0.3398664891719818, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -6.198605537414551, |
| "min": -6.198605537414551, |
| "max": 80.54835510253906, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06736716328235896, |
| "min": 0.0649744545202751, |
| "max": 0.07512444171264406, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9431402859530255, |
| "min": 0.5047755412046192, |
| "max": 1.0785371518366305, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01716888072232472, |
| "min": 0.0010650131654338034, |
| "max": 0.01716888072232472, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.24036433011254604, |
| "min": 0.014910184316073247, |
| "max": 0.24036433011254604, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.681559032204834e-06, |
| "min": 7.681559032204834e-06, |
| "max": 0.0002951506544346135, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010754182645086768, |
| "min": 0.00010754182645086768, |
| "max": 0.003632751325327273, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10256048719756403, |
| "min": 0.10256048719756403, |
| "max": 0.19838355093938814, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4358468207658963, |
| "min": 1.388684856575717, |
| "max": 2.6109170454147734, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002657926710366447, |
| "min": 0.0002657926710366447, |
| "max": 0.00983851673884488, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0037210973945130256, |
| "min": 0.0037210973945130256, |
| "max": 0.1211106128369358, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.011881115846335888, |
| "min": 0.011703819036483765, |
| "max": 0.47201913595199585, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.16633562743663788, |
| "min": 0.1638534665107727, |
| "max": 3.304133892059326, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 434.5217391304348, |
| "min": 434.5217391304348, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29982.0, |
| "min": 15984.0, |
| "max": 33351.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.4205101247930871, |
| "min": -1.0000000521540642, |
| "max": 1.4205101247930871, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 98.01519861072302, |
| "min": -28.288201674818993, |
| "max": 98.01519861072302, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.4205101247930871, |
| "min": -1.0000000521540642, |
| "max": 1.4205101247930871, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 98.01519861072302, |
| "min": -28.288201674818993, |
| "max": 98.01519861072302, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.05384381167401654, |
| "min": 0.05384381167401654, |
| "max": 9.738031914457679, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.7152230055071414, |
| "min": 3.4312176319072023, |
| "max": 155.80851063132286, |
| "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": "1758640046", |
| "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": "2.8.0+cu128", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1758642209" |
| }, |
| "total": 2162.849643356, |
| "count": 1, |
| "self": 0.4367271810001512, |
| "children": { |
| "run_training.setup": { |
| "total": 0.025391149000029145, |
| "count": 1, |
| "self": 0.025391149000029145 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2162.387525026, |
| "count": 1, |
| "self": 1.278527995993045, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.167463133999945, |
| "count": 1, |
| "self": 3.167463133999945 |
| }, |
| "TrainerController.advance": { |
| "total": 2157.868756267007, |
| "count": 63558, |
| "self": 1.3157456120316056, |
| "children": { |
| "env_step": { |
| "total": 1497.003978174025, |
| "count": 63558, |
| "self": 1350.5762405790229, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 145.64148828801262, |
| "count": 63558, |
| "self": 4.616500202048883, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 141.02498808596374, |
| "count": 62572, |
| "self": 141.02498808596374 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.7862493069895891, |
| "count": 63558, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2155.8369406349802, |
| "count": 63558, |
| "is_parallel": true, |
| "self": 921.0542261230155, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.004025597999998354, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0019996319999791012, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0020259660000192525, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0020259660000192525 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05706201400005284, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005309200000738201, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00044675999993160076, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00044675999993160076 |
| }, |
| "communicator.exchange": { |
| "total": 0.05446510900003432, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.05446510900003432 |
| }, |
| "steps_from_proto": { |
| "total": 0.0016192250000131025, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0003595849999555867, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012596400000575159, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012596400000575159 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1234.7827145119647, |
| "count": 63557, |
| "is_parallel": true, |
| "self": 33.81004708597379, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 22.739313305998166, |
| "count": 63557, |
| "is_parallel": true, |
| "self": 22.739313305998166 |
| }, |
| "communicator.exchange": { |
| "total": 1070.0312231510215, |
| "count": 63557, |
| "is_parallel": true, |
| "self": 1070.0312231510215 |
| }, |
| "steps_from_proto": { |
| "total": 108.20213096897123, |
| "count": 63557, |
| "is_parallel": true, |
| "self": 22.403760886160512, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 85.79837008281072, |
| "count": 508456, |
| "is_parallel": true, |
| "self": 85.79837008281072 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 659.5490324809505, |
| "count": 63558, |
| "self": 2.6097679099378865, |
| "children": { |
| "process_trajectory": { |
| "total": 125.92200888001366, |
| "count": 63558, |
| "self": 125.6748022400136, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.24720664000005854, |
| "count": 2, |
| "self": 0.24720664000005854 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 531.0172556909989, |
| "count": 457, |
| "self": 296.9065000169803, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 234.1107556740186, |
| "count": 22797, |
| "self": 234.1107556740186 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 8.050001270021312e-07, |
| "count": 1, |
| "self": 8.050001270021312e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.07277682399990226, |
| "count": 1, |
| "self": 0.0009314199996879324, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.07184540400021433, |
| "count": 1, |
| "self": 0.07184540400021433 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
