{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13946236670017242, "min": 0.13686366379261017, "max": 1.4176063537597656, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4181.6396484375, "min": 4075.25244140625, "max": 43004.5078125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999965.0, "min": 29952.0, "max": 2999965.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999965.0, "min": 29952.0, "max": 2999965.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7085632681846619, "min": -0.10780268907546997, "max": 0.8996084332466125, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 201.23196411132812, "min": -25.98044776916504, "max": 280.23077392578125, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0028057924937456846, "min": -0.03782700002193451, "max": 0.4121745824813843, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.7968450784683228, "min": -11.385927200317383, "max": 97.68537902832031, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06860144955724191, "min": 0.06302573735038527, "max": 0.07302680730666747, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9604202938013867, "min": 0.5009040097192856, "max": 1.0711029080557637, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014153322314086838, "min": 9.910044851201291e-05, "max": 0.016067825151879357, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19814651239721573, "min": 0.001189205382144155, "max": 0.23270540341150528, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4804066494214297e-06, "min": 1.4804066494214297e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0725693091900017e-05, "min": 2.0725693091900017e-05, "max": 0.0037254528581823995, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10049343571428572, "min": 0.10049343571428572, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4069081, "min": 1.3962282666666668, "max": 2.6474363000000003, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.929422785714291e-05, "min": 5.929422785714291e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008301191900000007, "min": 0.0008301191900000007, "max": 0.12418757823999997, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.005943336524069309, "min": 0.005910669453442097, "max": 0.4511844515800476, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08320671319961548, "min": 0.08320671319961548, "max": 3.1582911014556885, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 232.61417322834646, "min": 191.75641025641025, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29542.0, "min": 15984.0, "max": 33757.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7367126849435626, "min": -1.0000000521540642, "max": 1.8088598609160467, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 218.82579830288887, "min": -31.99760165810585, "max": 283.9909981638193, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7367126849435626, "min": -1.0000000521540642, "max": 1.8088598609160467, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 218.82579830288887, "min": -31.99760165810585, "max": 283.9909981638193, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.014327315880008327, "min": 0.01301729553052859, "max": 9.26777633652091, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 1.8052418008810491, "min": 1.719382760755252, "max": 148.28442138433456, "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": "1683539978", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1683547499" }, "total": 7521.638243533, "count": 1, "self": 0.44794141800048237, "children": { "run_training.setup": { "total": 0.03747426199993242, "count": 1, "self": 0.03747426199993242 }, "TrainerController.start_learning": { "total": 7521.1528278529995, "count": 1, "self": 4.552333467206154, "children": { "TrainerController._reset_env": { "total": 4.03394553499993, "count": 1, "self": 4.03394553499993 }, "TrainerController.advance": { "total": 7512.469312483794, "count": 195382, "self": 4.418412850948698, "children": { "env_step": { "total": 5576.213003565918, "count": 195382, "self": 5240.52437039088, "children": { "SubprocessEnvManager._take_step": { "total": 332.97450659988067, "count": 195382, "self": 14.682114550865663, "children": { "TorchPolicy.evaluate": { "total": 318.292392049015, "count": 187556, "self": 318.292392049015 } } }, "workers": { "total": 2.714126575157252, "count": 195382, "self": 0.0, "children": { "worker_root": { "total": 7504.02414595464, "count": 195382, "is_parallel": true, "self": 2619.7502666296296, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022400580000976333, "count": 1, "is_parallel": true, "self": 0.0005016249997424893, "children": { "_process_rank_one_or_two_observation": { "total": 0.001738433000355144, "count": 8, "is_parallel": true, "self": 0.001738433000355144 } } }, "UnityEnvironment.step": { "total": 0.10057041000004574, "count": 1, "is_parallel": true, "self": 0.0005417429999852175, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00043935400003647374, "count": 1, "is_parallel": true, "self": 0.00043935400003647374 }, "communicator.exchange": { "total": 0.09792319700000007, "count": 1, "is_parallel": true, "self": 0.09792319700000007 }, "steps_from_proto": { "total": 0.001666116000023976, "count": 1, "is_parallel": true, "self": 0.0003411949996916519, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013249210003323242, "count": 8, "is_parallel": true, "self": 0.0013249210003323242 } } } } } } }, "UnityEnvironment.step": { "total": 4884.27387932501, "count": 195381, "is_parallel": true, "self": 98.09291398061487, "children": { "UnityEnvironment._generate_step_input": { "total": 71.31786731406942, "count": 195381, "is_parallel": true, "self": 71.31786731406942 }, "communicator.exchange": { "total": 4410.533009657243, "count": 195381, "is_parallel": true, "self": 4410.533009657243 }, "steps_from_proto": { "total": 304.3300883730826, "count": 195381, "is_parallel": true, "self": 63.202674994349536, "children": { "_process_rank_one_or_two_observation": { "total": 241.12741337873308, "count": 1563048, "is_parallel": true, "self": 241.12741337873308 } } } } } } } } } } }, "trainer_advance": { "total": 1931.8378960669272, "count": 195382, "self": 8.51131409285722, "children": { "process_trajectory": { "total": 334.1785205640592, "count": 195382, "self": 333.47493093905837, "children": { "RLTrainer._checkpoint": { "total": 0.7035896250008591, "count": 6, "self": 0.7035896250008591 } } }, "_update_policy": { "total": 1589.1480614100108, "count": 1393, "self": 1023.9196602078655, "children": { "TorchPPOOptimizer.update": { "total": 565.2284012021453, "count": 68448, "self": 565.2284012021453 } } } } } } }, "trainer_threads": { "total": 1.0399999155197293e-06, "count": 1, "self": 1.0399999155197293e-06 }, "TrainerController._save_models": { "total": 0.09723532699899806, "count": 1, "self": 0.0015420199997606687, "children": { "RLTrainer._checkpoint": { "total": 0.09569330699923739, "count": 1, "self": 0.09569330699923739 } } } } } } }