{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.7123656868934631, "min": 0.6570796370506287, "max": 1.428212285041809, "count": 16 }, "Pyramids.Policy.Entropy.sum": { "value": 21462.154296875, "min": 19592.73828125, "max": 43326.24609375, "count": 16 }, "Pyramids.Step.mean": { "value": 479926.0, "min": 29975.0, "max": 479926.0, "count": 16 }, "Pyramids.Step.sum": { "value": 479926.0, "min": 29975.0, "max": 479926.0, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.08970457315444946, "min": -0.09704577177762985, "max": 0.08970457315444946, "count": 16 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 22.246734619140625, "min": -23.290985107421875, "max": 22.246734619140625, "count": 16 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.011859128251671791, "min": 0.007869926281273365, "max": 0.3850874602794647, "count": 16 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.94106388092041, "min": 1.904522180557251, "max": 91.65081787109375, "count": 16 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.066041112951805, "min": 0.06540364939514, "max": 0.07304739349894909, "count": 16 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9245755813252698, "min": 0.5493568023939963, "max": 1.0620316853061975, "count": 16 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00849363308773877, "min": 0.0010521916522333481, "max": 0.00849363308773877, "count": 16 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.11891086322834277, "min": 0.009469724870100133, "max": 0.11891086322834277, "count": 16 }, "Pyramids.Policy.LearningRate.mean": { "value": 2.1158192947300003e-05, "min": 2.1158192947300003e-05, "max": 0.00029001517832827497, "count": 16 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00029621470126220005, "min": 0.00029621470126220005, "max": 0.00285423034859, "count": 16 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10705270000000001, "min": 0.10705270000000001, "max": 0.19667172500000002, "count": 16 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4987378000000002, "min": 1.4987378000000002, "max": 2.3386889999999996, "count": 16 }, "Pyramids.Policy.Beta.mean": { "value": 0.0007145647300000002, "min": 0.0007145647300000002, "max": 0.0096675053275, "count": 16 }, "Pyramids.Policy.Beta.sum": { "value": 0.010003906220000002, "min": 0.010003906220000002, "max": 0.095175859, "count": 16 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01774653047323227, "min": 0.017288541421294212, "max": 0.3124820590019226, "count": 16 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.24845142662525177, "min": 0.24203957617282867, "max": 2.499856472015381, "count": 16 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 802.1621621621622, "min": 802.1621621621622, "max": 999.0, "count": 16 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29680.0, "min": 16261.0, "max": 32296.0, "count": 16 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.3867891382526707, "min": -0.999987552408129, "max": 0.3867891382526707, "count": 16 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 14.311198115348816, "min": -31.999601677060127, "max": 14.311198115348816, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.3867891382526707, "min": -0.999987552408129, "max": 0.3867891382526707, "count": 16 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 14.311198115348816, "min": -31.999601677060127, "max": 14.311198115348816, "count": 16 }, "Pyramids.Policy.RndReward.mean": { "value": 0.14845000534960245, "min": 0.14590737862965544, "max": 5.863223752213849, "count": 16 }, "Pyramids.Policy.RndReward.sum": { "value": 5.492650197935291, "min": 5.398573009297252, "max": 105.53802753984928, "count": 16 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 16 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1714871472", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=PyramidsTraining --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714872500" }, "total": 1028.622528084, "count": 1, "self": 0.8875892680000561, "children": { "run_training.setup": { "total": 0.05201031299998249, "count": 1, "self": 0.05201031299998249 }, "TrainerController.start_learning": { "total": 1027.6829285029999, "count": 1, "self": 0.685191689992962, "children": { "TrainerController._reset_env": { "total": 2.4036292729999786, "count": 1, "self": 2.4036292729999786 }, "TrainerController.advance": { "total": 1024.466851615007, "count": 31565, "self": 0.739460445024406, "children": { "env_step": { "total": 705.335465500984, "count": 31565, "self": 638.238447736984, "children": { "SubprocessEnvManager._take_step": { "total": 66.67324442501331, "count": 31565, "self": 2.351425785015522, "children": { "TorchPolicy.evaluate": { "total": 64.32181863999779, "count": 31310, "self": 64.32181863999779 } } }, "workers": { "total": 0.4237733389867344, "count": 31565, "self": 0.0, "children": { "worker_root": { "total": 1024.9422049909845, "count": 31565, "is_parallel": true, "self": 446.7417756769544, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002068883999982063, "count": 1, "is_parallel": true, "self": 0.0006114659997820127, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014574180002000503, "count": 8, "is_parallel": true, "self": 0.0014574180002000503 } } }, "UnityEnvironment.step": { "total": 0.09730432000003475, "count": 1, "is_parallel": true, "self": 0.0006878179999603162, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044245599997339013, "count": 1, "is_parallel": true, "self": 0.00044245599997339013 }, "communicator.exchange": { "total": 0.09450887100001637, "count": 1, "is_parallel": true, "self": 0.09450887100001637 }, "steps_from_proto": { "total": 0.0016651750000846732, "count": 1, "is_parallel": true, "self": 0.00033464000000549277, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013305350000791805, "count": 8, "is_parallel": true, "self": 0.0013305350000791805 } } } } } } }, "UnityEnvironment.step": { "total": 578.2004293140301, "count": 31564, "is_parallel": true, "self": 17.337495871061037, "children": { "UnityEnvironment._generate_step_input": { "total": 11.954495890984958, "count": 31564, "is_parallel": true, "self": 11.954495890984958 }, "communicator.exchange": { "total": 499.2348761090019, "count": 31564, "is_parallel": true, "self": 499.2348761090019 }, "steps_from_proto": { "total": 49.67356144298219, "count": 31564, "is_parallel": true, "self": 9.907257139067724, "children": { "_process_rank_one_or_two_observation": { "total": 39.76630430391447, "count": 252512, "is_parallel": true, "self": 39.76630430391447 } } } } } } } } } } }, "trainer_advance": { "total": 318.3919256689986, "count": 31565, "self": 1.1984411679775349, "children": { "process_trajectory": { "total": 63.746216941020975, "count": 31565, "self": 63.582973349020904, "children": { "RLTrainer._checkpoint": { "total": 0.16324359200007166, "count": 1, "self": 0.16324359200007166 } } }, "_update_policy": { "total": 253.4472675600001, "count": 215, "self": 148.8158095870142, "children": { "TorchPPOOptimizer.update": { "total": 104.63145797298591, "count": 11436, "self": 104.63145797298591 } } } } } } }, "trainer_threads": { "total": 1.3059998309472576e-06, "count": 1, "self": 1.3059998309472576e-06 }, "TrainerController._save_models": { "total": 0.1272546190000412, "count": 1, "self": 0.0022669290001431364, "children": { "RLTrainer._checkpoint": { "total": 0.12498768999989807, "count": 1, "self": 0.12498768999989807 } } } } } } }