{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.18285278975963593, "min": 0.15829557180404663, "max": 1.4323687553405762, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5468.02978515625, "min": 4723.5400390625, "max": 43452.33984375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999979.0, "min": 29935.0, "max": 2999979.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999979.0, "min": 29935.0, "max": 2999979.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6964827179908752, "min": -0.13970039784908295, "max": 0.7969334125518799, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 205.46240234375, "min": -33.66779708862305, "max": 237.90171813964844, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.005779228638857603, "min": -0.021685507148504257, "max": 0.2419811338186264, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.704872488975525, "min": -5.833401203155518, "max": 58.31745147705078, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06742259888103166, "min": 0.06501802642251227, "max": 0.07301930969305569, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9439163843344432, "min": 0.4808734027277772, "max": 1.0952896453958354, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016459554707537224, "min": 0.0008092728319497403, "max": 0.016467897725402914, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23043376590552114, "min": 0.010520546815346624, "max": 0.2377021069976264, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.491342360061905e-06, "min": 1.491342360061905e-06, "max": 0.00029841121481530953, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0878793040866668e-05, "min": 2.0878793040866668e-05, "max": 0.004027435157521667, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049708095238097, "min": 0.10049708095238097, "max": 0.19947040476190478, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069591333333336, "min": 1.3962928333333335, "max": 2.8424783333333337, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.9658387142857144e-05, "min": 5.9658387142857144e-05, "max": 0.009947093435714285, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.00083521742, "min": 0.00083521742, "max": 0.1342635855, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.004958438687026501, "min": 0.00427287956699729, "max": 0.2937656044960022, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.06941813975572586, "min": 0.05982031300663948, "max": 2.05635929107666, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 247.6290322580645, "min": 222.01503759398497, "max": 998.34375, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30706.0, "min": 16734.0, "max": 33112.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6871495845962345, "min": -0.9368000526446849, "max": 1.749907796853222, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 207.51939890533686, "min": -29.977601684629917, "max": 232.47119836509228, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6871495845962345, "min": -0.9368000526446849, "max": 1.749907796853222, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 207.51939890533686, "min": -29.977601684629917, "max": 232.47119836509228, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.012479931004125363, "min": 0.01105117074777289, "max": 5.1934937037089295, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.5350315135074197, "min": 1.224667076865444, "max": 88.2893929630518, "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 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1732077789", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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=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": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1732089075" }, "total": 11285.833580584, "count": 1, "self": 0.8443494309995003, "children": { "run_training.setup": { "total": 0.07867109900007563, "count": 1, "self": 0.07867109900007563 }, "TrainerController.start_learning": { "total": 11284.910560054, "count": 1, "self": 7.741886614343457, "children": { "TrainerController._reset_env": { "total": 3.482843707000029, "count": 1, "self": 3.482843707000029 }, "TrainerController.advance": { "total": 11273.555989525654, "count": 194216, "self": 8.001081808701201, "children": { "env_step": { "total": 7699.351743828071, "count": 194216, "self": 7159.420486455131, "children": { "SubprocessEnvManager._take_step": { "total": 535.3316907919439, "count": 194216, "self": 23.40677741187551, "children": { "TorchPolicy.evaluate": { "total": 511.92491338006835, "count": 187554, "self": 511.92491338006835 } } }, "workers": { "total": 4.599566580996225, "count": 194216, "self": 0.0, "children": { "worker_root": { "total": 11260.72128556809, "count": 194216, "is_parallel": true, "self": 4686.566188749397, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005457175000174175, "count": 1, "is_parallel": true, "self": 0.0012835189997986163, "children": { "_process_rank_one_or_two_observation": { "total": 0.0041736560003755585, "count": 8, "is_parallel": true, "self": 0.0041736560003755585 } } }, "UnityEnvironment.step": { "total": 0.11230226600014248, "count": 1, "is_parallel": true, "self": 0.0007726520004780468, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005379519998314208, "count": 1, "is_parallel": true, "self": 0.0005379519998314208 }, "communicator.exchange": { "total": 0.10886398100001315, "count": 1, "is_parallel": true, "self": 0.10886398100001315 }, "steps_from_proto": { "total": 0.0021276809998198587, "count": 1, "is_parallel": true, "self": 0.0004267109998181695, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017009700000016892, "count": 8, "is_parallel": true, "self": 0.0017009700000016892 } } } } } } }, "UnityEnvironment.step": { "total": 6574.155096818693, "count": 194215, "is_parallel": true, "self": 157.79142137453073, "children": { "UnityEnvironment._generate_step_input": { "total": 96.18945255909671, "count": 194215, "is_parallel": true, "self": 96.18945255909671 }, "communicator.exchange": { "total": 5908.715802249913, "count": 194215, "is_parallel": true, "self": 5908.715802249913 }, "steps_from_proto": { "total": 411.4584206351517, "count": 194215, "is_parallel": true, "self": 90.14596208571129, "children": { "_process_rank_one_or_two_observation": { "total": 321.3124585494404, "count": 1553720, "is_parallel": true, "self": 321.3124585494404 } } } } } } } } } } }, "trainer_advance": { "total": 3566.2031638888807, "count": 194216, "self": 15.025276234190187, "children": { "process_trajectory": { "total": 560.8966152936796, "count": 194216, "self": 560.1625903826794, "children": { "RLTrainer._checkpoint": { "total": 0.7340249110002333, "count": 6, "self": 0.7340249110002333 } } }, "_update_policy": { "total": 2990.281272361011, "count": 1400, "self": 1185.6133037929872, "children": { "TorchPPOOptimizer.update": { "total": 1804.6679685680238, "count": 68325, "self": 1804.6679685680238 } } } } } } }, "trainer_threads": { "total": 1.8700011423788965e-06, "count": 1, "self": 1.8700011423788965e-06 }, "TrainerController._save_models": { "total": 0.12983833700127434, "count": 1, "self": 0.0030599070014432073, "children": { "RLTrainer._checkpoint": { "total": 0.12677842999983113, "count": 1, "self": 0.12677842999983113 } } } } } } }