{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5320305824279785, "min": 0.5320305824279785, "max": 1.517937421798706, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 15918.35546875, "min": 15918.35546875, "max": 46048.1484375, "count": 33 }, "Pyramids.Step.mean": { "value": 989990.0, "min": 29952.0, "max": 989990.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989990.0, "min": 29952.0, "max": 989990.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.43827494978904724, "min": -0.21581387519836426, "max": 0.43827494978904724, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 119.64906311035156, "min": -51.14788818359375, "max": 119.64906311035156, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.07870253175497055, "min": -0.048301663249731064, "max": 0.23303084075450897, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 21.48579216003418, "min": -13.089750289916992, "max": 56.160430908203125, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06484102318617738, "min": 0.06484102318617738, "max": 0.07431993701423735, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9077743246064833, "min": 0.4997838062612907, "max": 1.0545000429396452, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.018193577836514343, "min": 0.0002528007962765459, "max": 0.018193577836514343, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2547100897112008, "min": 0.003286410351595097, "max": 0.2547100897112008, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.329418985464288e-06, "min": 7.329418985464288e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010261186579650003, "min": 0.00010261186579650003, "max": 0.0035080970306343995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10244310714285716, "min": 0.10244310714285716, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4342035000000002, "min": 1.3886848, "max": 2.5693656000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025406640357142867, "min": 0.00025406640357142867, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003556929650000001, "min": 0.003556929650000001, "max": 0.11695962344000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01078767143189907, "min": 0.01078767143189907, "max": 0.37173062562942505, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1510273963212967, "min": 0.1510273963212967, "max": 2.60211443901062, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 392.7142857142857, "min": 392.7142857142857, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30239.0, "min": 15984.0, "max": 33578.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.451386995613575, "min": -1.0000000521540642, "max": 1.451386995613575, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 111.75679866224527, "min": -31.995201662182808, "max": 111.75679866224527, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.451386995613575, "min": -1.0000000521540642, "max": 1.451386995613575, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 111.75679866224527, "min": -31.995201662182808, "max": 111.75679866224527, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.04463684560833862, "min": 0.04463684560833862, "max": 7.471085749566555, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.4370371118420735, "min": 3.4370371118420735, "max": 119.53737199306488, "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": "1769049987", "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": "1769053074" }, "total": 3087.3798807129997, "count": 1, "self": 0.821542209999734, "children": { "run_training.setup": { "total": 0.03582354399986798, "count": 1, "self": 0.03582354399986798 }, "TrainerController.start_learning": { "total": 3086.522514959, "count": 1, "self": 2.1420420370682223, "children": { "TrainerController._reset_env": { "total": 2.7332746269999006, "count": 1, "self": 2.7332746269999006 }, "TrainerController.advance": { "total": 3081.576767802932, "count": 63415, "self": 2.240406261042608, "children": { "env_step": { "total": 2040.1072057400083, "count": 63415, "self": 1884.068467199907, "children": { "SubprocessEnvManager._take_step": { "total": 154.68146757196791, "count": 63415, "self": 6.3448643529327455, "children": { "TorchPolicy.evaluate": { "total": 148.33660321903517, "count": 62557, "self": 148.33660321903517 } } }, "workers": { "total": 1.3572709681334345, "count": 63415, "self": 0.0, "children": { "worker_root": { "total": 3079.087881820979, "count": 63415, "is_parallel": true, "self": 1365.0729649500754, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002276233999964461, "count": 1, "is_parallel": true, "self": 0.0006669369995506713, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016092970004137896, "count": 8, "is_parallel": true, "self": 0.0016092970004137896 } } }, "UnityEnvironment.step": { "total": 0.06545808300006684, "count": 1, "is_parallel": true, "self": 0.0006074809998608544, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005427400001281057, "count": 1, "is_parallel": true, "self": 0.0005427400001281057 }, "communicator.exchange": { "total": 0.06214000199997827, "count": 1, "is_parallel": true, "self": 0.06214000199997827 }, "steps_from_proto": { "total": 0.0021678600000996084, "count": 1, "is_parallel": true, "self": 0.0004425009997248708, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017253590003747377, "count": 8, "is_parallel": true, "self": 0.0017253590003747377 } } } } } } }, "UnityEnvironment.step": { "total": 1714.0149168709036, "count": 63414, "is_parallel": true, "self": 43.442586692653094, "children": { "UnityEnvironment._generate_step_input": { "total": 28.942567593153854, "count": 63414, "is_parallel": true, "self": 28.942567593153854 }, "communicator.exchange": { "total": 1502.6338237330278, "count": 63414, "is_parallel": true, "self": 1502.6338237330278 }, "steps_from_proto": { "total": 138.99593885206878, "count": 63414, "is_parallel": true, "self": 28.11152411706007, "children": { "_process_rank_one_or_two_observation": { "total": 110.8844147350087, "count": 507312, "is_parallel": true, "self": 110.8844147350087 } } } } } } } } } } }, "trainer_advance": { "total": 1039.229155801881, "count": 63415, "self": 3.94685834907159, "children": { "process_trajectory": { "total": 150.1292560967995, "count": 63415, "self": 149.47218662279965, "children": { "RLTrainer._checkpoint": { "total": 0.6570694739998544, "count": 2, "self": 0.6570694739998544 } } }, "_update_policy": { "total": 885.1530413560099, "count": 447, "self": 350.15147616297054, "children": { "TorchPPOOptimizer.update": { "total": 535.0015651930394, "count": 22839, "self": 535.0015651930394 } } } } } } }, "trainer_threads": { "total": 1.1219999578315765e-06, "count": 1, "self": 1.1219999578315765e-06 }, "TrainerController._save_models": { "total": 0.07042937000005622, "count": 1, "self": 0.0015082740001162165, "children": { "RLTrainer._checkpoint": { "total": 0.06892109599994001, "count": 1, "self": 0.06892109599994001 } } } } } } }