{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2858012020587921, "min": 0.2858012020587921, "max": 1.594087839126587, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 2862.584716796875, "min": 2774.42724609375, "max": 16323.458984375, "count": 100 }, "Pyramids.Step.mean": { "value": 999990.0, "min": 9984.0, "max": 999990.0, "count": 100 }, "Pyramids.Step.sum": { "value": 999990.0, "min": 9984.0, "max": 999990.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.30679360032081604, "min": -0.056178826838731766, "max": 0.3858051598072052, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 28.53180503845215, "min": -4.606663703918457, "max": 37.80890655517578, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.004382860381156206, "min": -0.02060329169034958, "max": 0.4178072214126587, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.4076060354709625, "min": -1.9985193014144897, "max": 32.814308166503906, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06595719941143019, "min": 0.06152520001827118, "max": 0.0792817540618582, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.32978599705715095, "min": 0.14525458298960764, "max": 0.3767153315420728, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01797925207476296, "min": 2.65735022253466e-05, "max": 0.01891175268125759, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.0898962603738148, "min": 0.0001062940089013864, "max": 0.0898962603738148, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.486719504459996e-06, "min": 1.486719504459996e-06, "max": 0.0002981568006144, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.43359752229998e-06, "min": 7.43359752229998e-06, "max": 0.0013880076373307998, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049554000000001, "min": 0.10049554000000001, "max": 0.1993856, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.5024777, "min": 0.39717119999999995, "max": 0.9626692, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.9504445999999876e-05, "min": 5.9504445999999876e-05, "max": 0.00993862144, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0002975222299999994, "min": 0.0002975222299999994, "max": 0.04627065308, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.012814315967261791, "min": 0.01231659296900034, "max": 0.8745813369750977, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06407158076763153, "min": 0.049441322684288025, "max": 1.7491626739501953, "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 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 299.1034482758621, "min": 244.28125, "max": 999.0, "count": 98 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 8674.0, "min": 1087.0, "max": 15984.0, "count": 98 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7008965328849595, "min": -1.0000000521540642, "max": 1.7557187327183783, "count": 98 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 49.325999453663826, "min": -16.000000834465027, "max": 69.31419935822487, "count": 98 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7008965328849595, "min": -1.0000000521540642, "max": 1.7557187327183783, "count": 98 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 49.325999453663826, "min": -16.000000834465027, "max": 69.31419935822487, "count": 98 }, "Pyramids.Policy.RndReward.mean": { "value": 0.039447964000483525, "min": 0.03383406994908, "max": 9.812995640560985, "count": 98 }, "Pyramids.Policy.RndReward.sum": { "value": 1.1439909560140222, "min": 1.08269023837056, "max": 157.00793024897575, "count": 98 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1752842975", "python_version": "3.10.6 | packaged by conda-forge | (main, Aug 22 2022, 20:35:26) [GCC 10.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramidsv1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752845439" }, "total": 2464.214030317, "count": 1, "self": 0.4899619449997772, "children": { "run_training.setup": { "total": 0.024666472000035355, "count": 1, "self": 0.024666472000035355 }, "TrainerController.start_learning": { "total": 2463.6994019000003, "count": 1, "self": 1.7675338019976152, "children": { "TrainerController._reset_env": { "total": 3.4263262279999935, "count": 1, "self": 3.4263262279999935 }, "TrainerController.advance": { "total": 2458.3898080750027, "count": 64077, "self": 1.7879200639504234, "children": { "env_step": { "total": 1744.0304824430325, "count": 64077, "self": 1561.5172349240195, "children": { "SubprocessEnvManager._take_step": { "total": 181.38135838296625, "count": 64077, "self": 5.368290923997847, "children": { "TorchPolicy.evaluate": { "total": 176.0130674589684, "count": 62561, "self": 176.0130674589684 } } }, "workers": { "total": 1.131889136046766, "count": 64077, "self": 0.0, "children": { "worker_root": { "total": 2456.293742771994, "count": 64077, "is_parallel": true, "self": 1030.8177257340283, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004982630999961657, "count": 1, "is_parallel": true, "self": 0.003709649999791509, "children": { "_process_rank_one_or_two_observation": { "total": 0.001272981000170148, "count": 8, "is_parallel": true, "self": 0.001272981000170148 } } }, "UnityEnvironment.step": { "total": 0.04958578699995542, "count": 1, "is_parallel": true, "self": 0.0005508369999915885, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004771850000224731, "count": 1, "is_parallel": true, "self": 0.0004771850000224731 }, "communicator.exchange": { "total": 0.04699313099990832, "count": 1, "is_parallel": true, "self": 0.04699313099990832 }, "steps_from_proto": { "total": 0.0015646340000330383, "count": 1, "is_parallel": true, "self": 0.0003411609999375287, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012234730000955096, "count": 8, "is_parallel": true, "self": 0.0012234730000955096 } } } } } } }, "UnityEnvironment.step": { "total": 1425.4760170379657, "count": 64076, "is_parallel": true, "self": 36.20165030491421, "children": { "UnityEnvironment._generate_step_input": { "total": 24.670475659031695, "count": 64076, "is_parallel": true, "self": 24.670475659031695 }, "communicator.exchange": { "total": 1258.6616279560117, "count": 64076, "is_parallel": true, "self": 1258.6616279560117 }, "steps_from_proto": { "total": 105.94226311800833, "count": 64076, "is_parallel": true, "self": 22.573381405871828, "children": { "_process_rank_one_or_two_observation": { "total": 83.3688817121365, "count": 512608, "is_parallel": true, "self": 83.3688817121365 } } } } } } } } } } }, "trainer_advance": { "total": 712.57140556802, "count": 64077, "self": 3.49741638200976, "children": { "process_trajectory": { "total": 139.45466973801194, "count": 64077, "self": 139.11809110801187, "children": { "RLTrainer._checkpoint": { "total": 0.3365786300000764, "count": 2, "self": 0.3365786300000764 } } }, "_update_policy": { "total": 569.6193194479984, "count": 457, "self": 305.64342491300727, "children": { "TorchPPOOptimizer.update": { "total": 263.9758945349911, "count": 22767, "self": 263.9758945349911 } } } } } } }, "trainer_threads": { "total": 9.959999260900076e-07, "count": 1, "self": 9.959999260900076e-07 }, "TrainerController._save_models": { "total": 0.11573279899994304, "count": 1, "self": 0.0018516949999138888, "children": { "RLTrainer._checkpoint": { "total": 0.11388110400002915, "count": 1, "self": 0.11388110400002915 } } } } } } }