{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.48018190264701843, "min": 0.29809290170669556, "max": 1.609270453453064, "count": 5564 }, "Pyramids.Policy.Entropy.sum": { "value": 15.36582088470459, "min": 4.769486427307129, "max": 3295.785888671875, "count": 5564 }, "Pyramids.Step.mean": { "value": 999938.0, "min": 128.0, "max": 999938.0, "count": 8013 }, "Pyramids.Step.sum": { "value": 999938.0, "min": 128.0, "max": 999938.0, "count": 8013 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6090235114097595, "min": -0.18267610669136047, "max": 1.779097080230713, "count": 8013 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 0.6090235114097595, "min": -0.18267610669136047, "max": 2.9349684715270996, "count": 8013 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.7529672980308533, "min": -2.6109306812286377, "max": 1.5369911193847656, "count": 8013 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.7529672980308533, "min": -2.8789758682250977, "max": 1.9517099857330322, "count": 8013 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 8013 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 8013 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.05967576015973464, "min": 0.05225649633212015, "max": 0.093191156280227, "count": 440 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.05967576015973464, "min": 0.05225649633212015, "max": 0.093191156280227, "count": 440 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.04791275078120331, "min": 4.096566183708252e-05, "max": 0.07373145610714953, "count": 440 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.04791275078120331, "min": 4.096566183708252e-05, "max": 0.07373145610714953, "count": 440 }, "Pyramids.Policy.LearningRate.mean": { "value": 4.6689984440000056e-07, "min": 4.6689984440000056e-07, "max": 0.0002987712004096, "count": 440 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.6689984440000056e-07, "min": 4.6689984440000056e-07, "max": 0.0002987712004096, "count": 440 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10015560000000001, "min": 0.10015560000000001, "max": 0.19959039999999997, "count": 440 }, "Pyramids.Policy.Epsilon.sum": { "value": 0.10015560000000001, "min": 0.10015560000000001, "max": 0.19959039999999997, "count": 440 }, "Pyramids.Policy.Beta.mean": { "value": 2.554444000000002e-05, "min": 2.554444000000002e-05, "max": 0.009959080960000002, "count": 440 }, "Pyramids.Policy.Beta.sum": { "value": 2.554444000000002e-05, "min": 2.554444000000002e-05, "max": 0.009959080960000002, "count": 440 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009184012189507484, "min": 0.008418445475399494, "max": 0.6469921469688416, "count": 440 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.009184012189507484, "min": 0.008418445475399494, "max": 0.6469921469688416, "count": 440 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 11.0, "max": 999.0, "count": 919 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 999.0, "min": 11.0, "max": 15984.0, "count": 919 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6589999496936798, "min": -1.0000000521540642, "max": 1.9889999628067017, "count": 1166 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 1.6589999496936798, "min": -1.0000000521540642, "max": 4.815000057220459, "count": 1166 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6589999496936798, "min": -1.0000000521540642, "max": 1.9889999628067017, "count": 1166 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 1.6589999496936798, "min": -1.0000000521540642, "max": 4.815000057220459, "count": 1166 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03135890141129494, "min": 0.004081433173269033, "max": 6.433250069618225, "count": 1166 }, "Pyramids.Policy.RndReward.sum": { "value": 0.03135890141129494, "min": 0.004081433173269033, "max": 6.433250069618225, "count": 1166 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704034895", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=PyramidsTraining --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704036931" }, "total": 2036.72524935, "count": 1, "self": 0.49170865599990066, "children": { "run_training.setup": { "total": 0.0452882720001071, "count": 1, "self": 0.0452882720001071 }, "TrainerController.start_learning": { "total": 2036.188252422, "count": 1, "self": 1.2382923069731078, "children": { "TrainerController._reset_env": { "total": 2.0325155730001825, "count": 1, "self": 2.0325155730001825 }, "TrainerController.advance": { "total": 2032.8383778300267, "count": 63251, "self": 1.3917753349264785, "children": { "env_step": { "total": 1409.8417455580584, "count": 63251, "self": 1287.269173110054, "children": { "SubprocessEnvManager._take_step": { "total": 121.8179686249614, "count": 63251, "self": 4.506854764874333, "children": { "TorchPolicy.evaluate": { "total": 117.31111386008706, "count": 62562, "self": 117.31111386008706 } } }, "workers": { "total": 0.7546038230429986, "count": 63251, "self": 0.0, "children": { "worker_root": { "total": 2031.5094602028466, "count": 63251, "is_parallel": true, "self": 857.0263799787626, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017279210001106549, "count": 1, "is_parallel": true, "self": 0.0005442680007945455, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011836529993161093, "count": 8, "is_parallel": true, "self": 0.0011836529993161093 } } }, "UnityEnvironment.step": { "total": 0.04959300300015457, "count": 1, "is_parallel": true, "self": 0.0005915800006732752, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044920599975739606, "count": 1, "is_parallel": true, "self": 0.00044920599975739606 }, "communicator.exchange": { "total": 0.04688297799975771, "count": 1, "is_parallel": true, "self": 0.04688297799975771 }, "steps_from_proto": { "total": 0.0016692389999661827, "count": 1, "is_parallel": true, "self": 0.0004247789997862128, "children": { "_process_rank_one_or_two_observation": { "total": 0.00124446000017997, "count": 8, "is_parallel": true, "self": 0.00124446000017997 } } } } } } }, "UnityEnvironment.step": { "total": 1174.483080224084, "count": 63250, "is_parallel": true, "self": 33.75304913284708, "children": { "UnityEnvironment._generate_step_input": { "total": 23.193250067060944, "count": 63250, "is_parallel": true, "self": 23.193250067060944 }, "communicator.exchange": { "total": 1022.7778030772665, "count": 63250, "is_parallel": true, "self": 1022.7778030772665 }, "steps_from_proto": { "total": 94.75897794690945, "count": 63250, "is_parallel": true, "self": 18.507106582729193, "children": { "_process_rank_one_or_two_observation": { "total": 76.25187136418026, "count": 506000, "is_parallel": true, "self": 76.25187136418026 } } } } } } } } } } }, "trainer_advance": { "total": 621.6048569370419, "count": 63251, "self": 2.257398964080039, "children": { "process_trajectory": { "total": 134.2001486679692, "count": 63251, "self": 134.01751130796947, "children": { "RLTrainer._checkpoint": { "total": 0.18263735999971686, "count": 2, "self": 0.18263735999971686 } } }, "_update_policy": { "total": 485.14730930499263, "count": 440, "self": 285.9545768540165, "children": { "TorchPPOOptimizer.update": { "total": 199.1927324509761, "count": 22806, "self": 199.1927324509761 } } } } } } }, "trainer_threads": { "total": 8.560000424040481e-07, "count": 1, "self": 8.560000424040481e-07 }, "TrainerController._save_models": { "total": 0.07906585599994287, "count": 1, "self": 0.001403623999976844, "children": { "RLTrainer._checkpoint": { "total": 0.07766223199996602, "count": 1, "self": 0.07766223199996602 } } } } } } }