{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.40284815430641174, "min": 0.40284815430641174, "max": 1.4012528657913208, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12259.474609375, "min": 12259.474609375, "max": 42508.40625, "count": 33 }, "Pyramids.Step.mean": { "value": 989935.0, "min": 29980.0, "max": 989935.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989935.0, "min": 29980.0, "max": 989935.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5704925060272217, "min": -0.10556398332118988, "max": 0.5704925060272217, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 162.59036254882812, "min": -25.335355758666992, "max": 162.59036254882812, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.04883839190006256, "min": -0.04883839190006256, "max": 0.27448779344558716, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -13.918941497802734, "min": -13.918941497802734, "max": 65.32809448242188, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06544708400657882, "min": 0.06514280284018777, "max": 0.07433934292355279, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9162591760921036, "min": 0.5947147433884223, "max": 1.0776343696246233, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.02130759619752758, "min": 0.0004814415739981965, "max": 0.02130759619752758, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2983063467653861, "min": 0.0052958573139801615, "max": 0.2983063467653861, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.508668925714285e-06, "min": 7.508668925714285e-06, "max": 0.00029521995159335, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010512136495999999, "min": 0.00010512136495999999, "max": 0.0033736378754540995, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10250285714285715, "min": 0.10250285714285715, "max": 0.19840665000000002, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.43504, "min": 1.43504, "max": 2.5725626999999998, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002600354285714285, "min": 0.0002600354285714285, "max": 0.009840824335000001, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003640495999999999, "min": 0.003640495999999999, "max": 0.11247213541000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008158338256180286, "min": 0.007725429721176624, "max": 0.384444922208786, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11421672999858856, "min": 0.10815601795911789, "max": 3.075559377670288, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 306.625, "min": 305.08, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29436.0, "min": 16779.0, "max": 33783.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6733876075019543, "min": -0.9999742457462896, "max": 1.6733876075019543, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 162.31859792768955, "min": -30.999201618134975, "max": 162.31859792768955, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6733876075019543, "min": -0.9999742457462896, "max": 1.6733876075019543, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 162.31859792768955, "min": -30.999201618134975, "max": 162.31859792768955, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.025970188705727683, "min": 0.025616552726867005, "max": 7.830660303068512, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.5191083044555853, "min": 2.3524736704912357, "max": 133.1212251521647, "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": "1748723253", "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": "1748725715" }, "total": 2462.634472048, "count": 1, "self": 0.5360109530001864, "children": { "run_training.setup": { "total": 0.020069938999768056, "count": 1, "self": 0.020069938999768056 }, "TrainerController.start_learning": { "total": 2462.078391156, "count": 1, "self": 1.6856279999769868, "children": { "TrainerController._reset_env": { "total": 2.6943522689998645, "count": 1, "self": 2.6943522689998645 }, "TrainerController.advance": { "total": 2457.606504949023, "count": 63974, "self": 1.721318006083493, "children": { "env_step": { "total": 1751.9083098689762, "count": 63974, "self": 1581.947501698989, "children": { "SubprocessEnvManager._take_step": { "total": 169.00696357689094, "count": 63974, "self": 5.351032756886525, "children": { "TorchPolicy.evaluate": { "total": 163.65593082000441, "count": 62549, "self": 163.65593082000441 } } }, "workers": { "total": 0.9538445930961643, "count": 63974, "self": 0.0, "children": { "worker_root": { "total": 2456.6913225071444, "count": 63974, "is_parallel": true, "self": 1001.1510720929514, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022845869998491253, "count": 1, "is_parallel": true, "self": 0.000742709999485669, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015418770003634563, "count": 8, "is_parallel": true, "self": 0.0015418770003634563 } } }, "UnityEnvironment.step": { "total": 0.07688090999999986, "count": 1, "is_parallel": true, "self": 0.0005333899998731795, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004542189999483526, "count": 1, "is_parallel": true, "self": 0.0004542189999483526 }, "communicator.exchange": { "total": 0.07435308100002658, "count": 1, "is_parallel": true, "self": 0.07435308100002658 }, "steps_from_proto": { "total": 0.0015402200001517485, "count": 1, "is_parallel": true, "self": 0.00031070700015334296, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012295129999984056, "count": 8, "is_parallel": true, "self": 0.0012295129999984056 } } } } } } }, "UnityEnvironment.step": { "total": 1455.540250414193, "count": 63973, "is_parallel": true, "self": 34.012972167301086, "children": { "UnityEnvironment._generate_step_input": { "total": 24.892488780977146, "count": 63973, "is_parallel": true, "self": 24.892488780977146 }, "communicator.exchange": { "total": 1290.2550729879827, "count": 63973, "is_parallel": true, "self": 1290.2550729879827 }, "steps_from_proto": { "total": 106.3797164779321, "count": 63973, "is_parallel": true, "self": 22.435850240591662, "children": { "_process_rank_one_or_two_observation": { "total": 83.94386623734044, "count": 511784, "is_parallel": true, "self": 83.94386623734044 } } } } } } } } } } }, "trainer_advance": { "total": 703.9768770739634, "count": 63974, "self": 3.120082186980653, "children": { "process_trajectory": { "total": 139.2689215849855, "count": 63974, "self": 139.04661289598562, "children": { "RLTrainer._checkpoint": { "total": 0.222308688999874, "count": 2, "self": 0.222308688999874 } } }, "_update_policy": { "total": 561.5878733019972, "count": 453, "self": 312.3422339560161, "children": { "TorchPPOOptimizer.update": { "total": 249.2456393459811, "count": 22812, "self": 249.2456393459811 } } } } } } }, "trainer_threads": { "total": 1.0570001904852688e-06, "count": 1, "self": 1.0570001904852688e-06 }, "TrainerController._save_models": { "total": 0.09190488100011862, "count": 1, "self": 0.0015395070004160516, "children": { "RLTrainer._checkpoint": { "total": 0.09036537399970257, "count": 1, "self": 0.09036537399970257 } } } } } } }