{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.742377519607544, "min": 0.6037590503692627, "max": 1.5161547660827637, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 22354.47265625, "min": 18035.490234375, "max": 45994.0703125, "count": 33 }, "Pyramids.Step.mean": { "value": 989910.0, "min": 29919.0, "max": 989910.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989910.0, "min": 29919.0, "max": 989910.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.23036058247089386, "min": -0.08066277951002121, "max": 0.4103885889053345, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 58.281227111816406, "min": -19.601055145263672, "max": 108.70287322998047, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -1.4734747409820557, "min": -2.698620319366455, "max": 0.6589729189872742, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -372.78912353515625, "min": -714.1650390625, "max": 172.65090942382812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06500626746326241, "min": 0.0645674482177984, "max": 0.07799872365695228, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9100877444856736, "min": 0.5640086917003269, "max": 1.0930318143412783, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.2666194773230543, "min": 0.00015690971780369384, "max": 0.7402144845885534, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 3.73267268252276, "min": 0.00203982633144802, "max": 11.1032172688283, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.546276056035721e-06, "min": 7.546276056035721e-06, "max": 0.0002952118890960375, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010564786478450009, "min": 0.00010564786478450009, "max": 0.003508371830542799, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251539285714287, "min": 0.10251539285714287, "max": 0.19840396249999998, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352155000000002, "min": 1.4352155000000002, "max": 2.5694572, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00026128774642857164, "min": 0.00026128774642857164, "max": 0.00984055585375, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036580284500000028, "min": 0.0036580284500000028, "max": 0.11696877427999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007733760867267847, "min": 0.007733760867267847, "max": 0.28628459572792053, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.10827264934778214, "min": 0.10827264934778214, "max": 2.2902767658233643, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 643.0, "min": 449.77941176470586, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28935.0, "min": 15951.0, "max": 33030.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.82346663756503, "min": -0.9998839233190783, "max": 1.3939967481119018, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 37.05599869042635, "min": -30.996401622891426, "max": 91.41079838573933, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.82346663756503, "min": -0.9998839233190783, "max": 1.3939967481119018, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 37.05599869042635, "min": -30.996401622891426, "max": 91.41079838573933, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05269231721241441, "min": 0.03951463343112076, "max": 6.242265203036368, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.3711542745586485, "min": 2.363360679068137, "max": 99.87624324858189, "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": "1746862659", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1746864855" }, "total": 2196.6766035620003, "count": 1, "self": 0.4931275839999216, "children": { "run_training.setup": { "total": 0.019536659000095824, "count": 1, "self": 0.019536659000095824 }, "TrainerController.start_learning": { "total": 2196.1639393190003, "count": 1, "self": 1.3853035230322348, "children": { "TrainerController._reset_env": { "total": 2.235166421000031, "count": 1, "self": 2.235166421000031 }, "TrainerController.advance": { "total": 2192.456865263968, "count": 63464, "self": 1.4483346839479054, "children": { "env_step": { "total": 1523.4718620070553, "count": 63464, "self": 1368.4643911510445, "children": { "SubprocessEnvManager._take_step": { "total": 154.17787470797657, "count": 63464, "self": 4.737615320963869, "children": { "TorchPolicy.evaluate": { "total": 149.4402593870127, "count": 62545, "self": 149.4402593870127 } } }, "workers": { "total": 0.8295961480341703, "count": 63464, "self": 0.0, "children": { "worker_root": { "total": 2191.0306847260617, "count": 63464, "is_parallel": true, "self": 937.3133272390005, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020052350000696606, "count": 1, "is_parallel": true, "self": 0.0006971000002522487, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013081349998174119, "count": 8, "is_parallel": true, "self": 0.0013081349998174119 } } }, "UnityEnvironment.step": { "total": 0.055620284000042375, "count": 1, "is_parallel": true, "self": 0.0005478389998643252, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005024440001761832, "count": 1, "is_parallel": true, "self": 0.0005024440001761832 }, "communicator.exchange": { "total": 0.05291496400013784, "count": 1, "is_parallel": true, "self": 0.05291496400013784 }, "steps_from_proto": { "total": 0.0016550369998640235, "count": 1, "is_parallel": true, "self": 0.00035225200008426327, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013027849997797603, "count": 8, "is_parallel": true, "self": 0.0013027849997797603 } } } } } } }, "UnityEnvironment.step": { "total": 1253.7173574870612, "count": 63463, "is_parallel": true, "self": 31.810354294097124, "children": { "UnityEnvironment._generate_step_input": { "total": 23.413942230036582, "count": 63463, "is_parallel": true, "self": 23.413942230036582 }, "communicator.exchange": { "total": 1100.0486985668972, "count": 63463, "is_parallel": true, "self": 1100.0486985668972 }, "steps_from_proto": { "total": 98.44436239603033, "count": 63463, "is_parallel": true, "self": 20.135389918776355, "children": { "_process_rank_one_or_two_observation": { "total": 78.30897247725397, "count": 507704, "is_parallel": true, "self": 78.30897247725397 } } } } } } } } } } }, "trainer_advance": { "total": 667.5366685729653, "count": 63464, "self": 2.712510388987994, "children": { "process_trajectory": { "total": 129.0287465069764, "count": 63464, "self": 128.7663129299758, "children": { "RLTrainer._checkpoint": { "total": 0.2624335770005928, "count": 2, "self": 0.2624335770005928 } } }, "_update_policy": { "total": 535.7954116770009, "count": 456, "self": 298.3097197589607, "children": { "TorchPPOOptimizer.update": { "total": 237.48569191804017, "count": 22773, "self": 237.48569191804017 } } } } } } }, "trainer_threads": { "total": 8.980000529845711e-07, "count": 1, "self": 8.980000529845711e-07 }, "TrainerController._save_models": { "total": 0.08660321299976204, "count": 1, "self": 0.0013396759995885077, "children": { "RLTrainer._checkpoint": { "total": 0.08526353700017353, "count": 1, "self": 0.08526353700017353 } } } } } } }