{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2097523957490921, "min": 0.2097523957490921, "max": 1.493598222732544, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 6265.7236328125, "min": 6265.7236328125, "max": 45309.796875, "count": 50 }, "Pyramids.Step.mean": { "value": 1499872.0, "min": 29952.0, "max": 1499872.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499872.0, "min": 29952.0, "max": 1499872.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7323671579360962, "min": -0.1035352349281311, "max": 0.7629164457321167, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 216.04830932617188, "min": -25.055526733398438, "max": 228.1120147705078, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.024602683261036873, "min": -0.017261844128370285, "max": 0.22436076402664185, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.257791519165039, "min": -4.988673210144043, "max": 53.84658432006836, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06738698095848251, "min": 0.06407559036786918, "max": 0.07424134721520527, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9434177334187551, "min": 0.5104810356422751, "max": 1.058787802117877, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017023766551513084, "min": 0.0009166898601802243, "max": 0.017023766551513084, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2383327317211832, "min": 0.00641682902126157, "max": 0.24216461378576543, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.160256089471428e-06, "min": 3.160256089471428e-06, "max": 0.00029676708679192377, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.4243585252599994e-05, "min": 4.4243585252599994e-05, "max": 0.0034729651423449997, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10105338571428572, "min": 0.10105338571428572, "max": 0.19892236190476195, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4147474000000002, "min": 1.3794090666666667, "max": 2.5343560666666667, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.00011523323285714286, "min": 0.00011523323285714286, "max": 0.009892343954285714, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.00161326526, "min": 0.00161326526, "max": 0.1157797345, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009697283618152142, "min": 0.009697283618152142, "max": 0.36767488718032837, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13576197624206543, "min": 0.13576197624206543, "max": 2.5737242698669434, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 252.35593220338984, "min": 236.8796992481203, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29778.0, "min": 15984.0, "max": 33111.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7476440568344067, "min": -1.0000000521540642, "max": 1.7476440568344067, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 206.22199870646, "min": -32.000001668930054, "max": 228.83399833738804, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7476440568344067, "min": -1.0000000521540642, "max": 1.7476440568344067, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 206.22199870646, "min": -32.000001668930054, "max": 228.83399833738804, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.025343465129450217, "min": 0.024217579453485967, "max": 6.98977246042341, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9905288852751255, "min": 2.9114665780653013, "max": 111.83635936677456, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1697462316", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697464661" }, "total": 2344.444770566, "count": 1, "self": 0.3218462660001933, "children": { "run_training.setup": { "total": 0.04271605299993553, "count": 1, "self": 0.04271605299993553 }, "TrainerController.start_learning": { "total": 2344.080208247, "count": 1, "self": 1.8659408659927976, "children": { "TrainerController._reset_env": { "total": 8.417073597000012, "count": 1, "self": 8.417073597000012 }, "TrainerController.advance": { "total": 2333.728816466007, "count": 96582, "self": 1.8694936790971042, "children": { "env_step": { "total": 1533.4879481329328, "count": 96582, "self": 1359.780631651915, "children": { "SubprocessEnvManager._take_step": { "total": 172.53304720501353, "count": 96582, "self": 6.34598913101695, "children": { "TorchPolicy.evaluate": { "total": 166.18705807399658, "count": 93806, "self": 166.18705807399658 } } }, "workers": { "total": 1.174269276004452, "count": 96582, "self": 0.0, "children": { "worker_root": { "total": 2341.102420435947, "count": 96582, "is_parallel": true, "self": 1118.400173227919, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0051776069999505125, "count": 1, "is_parallel": true, "self": 0.0038569949998645825, "children": { "_process_rank_one_or_two_observation": { "total": 0.00132061200008593, "count": 8, "is_parallel": true, "self": 0.00132061200008593 } } }, "UnityEnvironment.step": { "total": 0.035204239999984566, "count": 1, "is_parallel": true, "self": 0.000330158999872765, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030958700006067374, "count": 1, "is_parallel": true, "self": 0.00030958700006067374 }, "communicator.exchange": { "total": 0.033601556000007804, "count": 1, "is_parallel": true, "self": 0.033601556000007804 }, "steps_from_proto": { "total": 0.000962938000043323, "count": 1, "is_parallel": true, "self": 0.0002212020000342818, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007417360000090412, "count": 8, "is_parallel": true, "self": 0.0007417360000090412 } } } } } } }, "UnityEnvironment.step": { "total": 1222.702247208028, "count": 96581, "is_parallel": true, "self": 30.89930734996142, "children": { "UnityEnvironment._generate_step_input": { "total": 21.555562532013482, "count": 96581, "is_parallel": true, "self": 21.555562532013482 }, "communicator.exchange": { "total": 1082.0822710419789, "count": 96581, "is_parallel": true, "self": 1082.0822710419789 }, "steps_from_proto": { "total": 88.16510628407411, "count": 96581, "is_parallel": true, "self": 19.367069528034335, "children": { "_process_rank_one_or_two_observation": { "total": 68.79803675603978, "count": 772648, "is_parallel": true, "self": 68.79803675603978 } } } } } } } } } } }, "trainer_advance": { "total": 798.3713746539771, "count": 96582, "self": 3.7253303899469756, "children": { "process_trajectory": { "total": 153.23227832303076, "count": 96582, "self": 152.92836154303075, "children": { "RLTrainer._checkpoint": { "total": 0.30391678000000866, "count": 3, "self": 0.30391678000000866 } } }, "_update_policy": { "total": 641.4137659409994, "count": 679, "self": 373.8677256929635, "children": { "TorchPPOOptimizer.update": { "total": 267.54604024803587, "count": 34176, "self": 267.54604024803587 } } } } } } }, "trainer_threads": { "total": 1.160000010713702e-06, "count": 1, "self": 1.160000010713702e-06 }, "TrainerController._save_models": { "total": 0.06837615799986452, "count": 1, "self": 0.001238759999978356, "children": { "RLTrainer._checkpoint": { "total": 0.06713739799988616, "count": 1, "self": 0.06713739799988616 } } } } } } }