{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5673871040344238, "min": 0.5673871040344238, "max": 1.5468554496765137, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16930.83203125, "min": 16930.83203125, "max": 46925.40625, "count": 33 }, "Pyramids.Step.mean": { "value": 989889.0, "min": 29952.0, "max": 989889.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989889.0, "min": 29952.0, "max": 989889.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.42564475536346436, "min": -0.12350236624479294, "max": 0.42564475536346436, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 114.4984359741211, "min": -29.270061492919922, "max": 114.4984359741211, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007162606809288263, "min": -0.016387740150094032, "max": 0.08205876499414444, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.9267412424087524, "min": -4.293587684631348, "max": 19.77616310119629, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06871854688506573, "min": 0.06424649954091624, "max": 0.07344178410169012, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.030778203275986, "min": 0.48504128212065045, "max": 1.0627033746956538, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015125677523448958, "min": 0.0005449440095225296, "max": 0.015125677523448958, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22688516285173438, "min": 0.004359552076180237, "max": 0.22688516285173438, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.54047748654e-06, "min": 7.54047748654e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011310716229810001, "min": 0.00011310716229810001, "max": 0.0035081999306001, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10251346, "min": 0.10251346, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5377019, "min": 1.3691136000000002, "max": 2.5693999, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.000261094654, "min": 0.000261094654, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.00391641981, "min": 0.00391641981, "max": 0.11696305001000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007876956835389137, "min": 0.007840299978852272, "max": 0.22394680976867676, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11815434694290161, "min": 0.10976419597864151, "max": 1.5676276683807373, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 423.28169014084506, "min": 406.3529411764706, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30053.0, "min": 15984.0, "max": 33143.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.4921858970757942, "min": -1.0000000521540642, "max": 1.4921858970757942, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 105.94519869238138, "min": -32.000001668930054, "max": 105.94519869238138, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.4921858970757942, "min": -1.0000000521540642, "max": 1.4921858970757942, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 105.94519869238138, "min": -32.000001668930054, "max": 105.94519869238138, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03461577750731778, "min": 0.03374406788541602, "max": 4.1653403653763235, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.457720203019562, "min": 2.260852548322873, "max": 66.64544584602118, "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": "1769216901", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/kaneki/miniconda3/envs/deepRL2/bin/mlagents-learn ../unit1/ml-agents/config/ppo/PyramidsRND.yaml --env=../unit1/trained-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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1769217903" }, "total": 1002.0556222120003, "count": 1, "self": 0.3188660480004728, "children": { "run_training.setup": { "total": 0.01972107900019182, "count": 1, "self": 0.01972107900019182 }, "TrainerController.start_learning": { "total": 1001.7170350849997, "count": 1, "self": 0.9307225709349041, "children": { "TrainerController._reset_env": { "total": 2.0634605029999875, "count": 1, "self": 2.0634605029999875 }, "TrainerController.advance": { "total": 998.6476304910648, "count": 63570, "self": 0.8760381172078269, "children": { "env_step": { "total": 600.0874692459229, "count": 63570, "self": 496.10778970593674, "children": { "SubprocessEnvManager._take_step": { "total": 103.3920676989992, "count": 63570, "self": 2.4090505309886794, "children": { "TorchPolicy.evaluate": { "total": 100.98301716801052, "count": 62557, "self": 100.98301716801052 } } }, "workers": { "total": 0.5876118409869378, "count": 63570, "self": 0.0, "children": { "worker_root": { "total": 1000.4258907030371, "count": 63570, "is_parallel": true, "self": 561.5268660860456, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001076188999832084, "count": 1, "is_parallel": true, "self": 0.0003325999982735084, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007435890015585755, "count": 8, "is_parallel": true, "self": 0.0007435890015585755 } } }, "UnityEnvironment.step": { "total": 0.02170786600026986, "count": 1, "is_parallel": true, "self": 0.0003551889999471314, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033385000006092014, "count": 1, "is_parallel": true, "self": 0.00033385000006092014 }, "communicator.exchange": { "total": 0.02000464799994006, "count": 1, "is_parallel": true, "self": 0.02000464799994006 }, "steps_from_proto": { "total": 0.0010141790003217466, "count": 1, "is_parallel": true, "self": 0.00022089000049163587, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007932889998301107, "count": 8, "is_parallel": true, "self": 0.0007932889998301107 } } } } } } }, "UnityEnvironment.step": { "total": 438.8990246169915, "count": 63569, "is_parallel": true, "self": 13.256880863980314, "children": { "UnityEnvironment._generate_step_input": { "total": 9.778342554031951, "count": 63569, "is_parallel": true, "self": 9.778342554031951 }, "communicator.exchange": { "total": 377.85664924599814, "count": 63569, "is_parallel": true, "self": 377.85664924599814 }, "steps_from_proto": { "total": 38.007151952981076, "count": 63569, "is_parallel": true, "self": 8.711370704029378, "children": { "_process_rank_one_or_two_observation": { "total": 29.295781248951698, "count": 508552, "is_parallel": true, "self": 29.295781248951698 } } } } } } } } } } }, "trainer_advance": { "total": 397.6841231279341, "count": 63570, "self": 1.828595488007977, "children": { "process_trajectory": { "total": 76.86674352791988, "count": 63570, "self": 76.7299087269198, "children": { "RLTrainer._checkpoint": { "total": 0.13683480100007728, "count": 2, "self": 0.13683480100007728 } } }, "_update_policy": { "total": 318.9887841120062, "count": 444, "self": 172.87732822099179, "children": { "TorchPPOOptimizer.update": { "total": 146.11145589101443, "count": 22806, "self": 146.11145589101443 } } } } } } }, "trainer_threads": { "total": 1.1399997674743645e-06, "count": 1, "self": 1.1399997674743645e-06 }, "TrainerController._save_models": { "total": 0.07522038000024622, "count": 1, "self": 0.0012142580003455805, "children": { "RLTrainer._checkpoint": { "total": 0.07400612199990064, "count": 1, "self": 0.07400612199990064 } } } } } } }