{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.41400235891342163, "min": 0.41400235891342163, "max": 1.449265480041504, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12612.16796875, "min": 12305.5576171875, "max": 43964.91796875, "count": 33 }, "Pyramids.Step.mean": { "value": 989910.0, "min": 29952.0, "max": 989910.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989910.0, "min": 29952.0, "max": 989910.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.4304543137550354, "min": -0.14936961233615875, "max": 0.5114449262619019, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 114.93130493164062, "min": -35.400596618652344, "max": 141.6702423095703, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0074755121022462845, "min": -0.2375980168581009, "max": 0.22314144670963287, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -1.9959617853164673, "min": -63.201072692871094, "max": 53.7770881652832, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06908204150565507, "min": 0.06431460470498894, "max": 0.07273331168877083, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9671485810791709, "min": 0.4841378116699193, "max": 1.0804228196491248, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01169383330239771, "min": 0.0002888783122543076, "max": 0.01874270626112342, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.16371366623356795, "min": 0.0025999048102887685, "max": 0.26239788765572786, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.408833244707146e-06, "min": 7.408833244707146e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010372366542590005, "min": 0.00010372366542590005, "max": 0.003508905230364999, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246957857142858, "min": 0.10246957857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4345741, "min": 1.3886848, "max": 2.569635, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025671089928571436, "min": 0.00025671089928571436, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035939525900000008, "min": 0.0035939525900000008, "max": 0.11698653650000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011938778683543205, "min": 0.01193359773606062, "max": 0.4032398760318756, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16714289784431458, "min": 0.16707037389278412, "max": 2.822679042816162, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 442.1969696969697, "min": 366.9024390243902, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29185.0, "min": 15984.0, "max": 33008.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.3153272500318107, "min": -1.0000000521540642, "max": 1.559899977976229, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 86.81159850209951, "min": -31.997201651334763, "max": 127.91179819405079, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.3153272500318107, "min": -1.0000000521540642, "max": 1.559899977976229, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 86.81159850209951, "min": -31.997201651334763, "max": 127.91179819405079, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.05467901877295155, "min": 0.04509352231359183, "max": 7.617507545277476, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.6088152390148025, "min": 3.6088152390148025, "max": 121.88012072443962, "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": "1724370971", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724373115" }, "total": 2144.623986979, "count": 1, "self": 0.7467439840002044, "children": { "run_training.setup": { "total": 0.05407538300005399, "count": 1, "self": 0.05407538300005399 }, "TrainerController.start_learning": { "total": 2143.823167612, "count": 1, "self": 1.5009261380500902, "children": { "TrainerController._reset_env": { "total": 2.2334466749998683, "count": 1, "self": 2.2334466749998683 }, "TrainerController.advance": { "total": 2139.96307776595, "count": 63552, "self": 1.572682422948219, "children": { "env_step": { "total": 1494.4089786339603, "count": 63552, "self": 1354.0970882829176, "children": { "SubprocessEnvManager._take_step": { "total": 139.40267717105849, "count": 63552, "self": 4.90044644104637, "children": { "TorchPolicy.evaluate": { "total": 134.50223073001212, "count": 62560, "self": 134.50223073001212 } } }, "workers": { "total": 0.9092131799841354, "count": 63552, "self": 0.0, "children": { "worker_root": { "total": 2138.4942655470054, "count": 63552, "is_parallel": true, "self": 911.1860538420055, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002054245000181254, "count": 1, "is_parallel": true, "self": 0.0006227400001534988, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014315050000277552, "count": 8, "is_parallel": true, "self": 0.0014315050000277552 } } }, "UnityEnvironment.step": { "total": 0.04999128700001165, "count": 1, "is_parallel": true, "self": 0.0006396849998964171, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004507119999743736, "count": 1, "is_parallel": true, "self": 0.0004507119999743736 }, "communicator.exchange": { "total": 0.047256940000124814, "count": 1, "is_parallel": true, "self": 0.047256940000124814 }, "steps_from_proto": { "total": 0.0016439500000160479, "count": 1, "is_parallel": true, "self": 0.00034039899946947116, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013035510005465767, "count": 8, "is_parallel": true, "self": 0.0013035510005465767 } } } } } } }, "UnityEnvironment.step": { "total": 1227.3082117049998, "count": 63551, "is_parallel": true, "self": 34.438383194025846, "children": { "UnityEnvironment._generate_step_input": { "total": 22.539817822005034, "count": 63551, "is_parallel": true, "self": 22.539817822005034 }, "communicator.exchange": { "total": 1071.3320255979504, "count": 63551, "is_parallel": true, "self": 1071.3320255979504 }, "steps_from_proto": { "total": 98.99798509101856, "count": 63551, "is_parallel": true, "self": 20.367871933020297, "children": { "_process_rank_one_or_two_observation": { "total": 78.63011315799827, "count": 508408, "is_parallel": true, "self": 78.63011315799827 } } } } } } } } } } }, "trainer_advance": { "total": 643.9814167090415, "count": 63552, "self": 3.0772849869599668, "children": { "process_trajectory": { "total": 129.8909660210786, "count": 63552, "self": 129.66119263807855, "children": { "RLTrainer._checkpoint": { "total": 0.22977338300006522, "count": 2, "self": 0.22977338300006522 } } }, "_update_policy": { "total": 511.0131657010029, "count": 448, "self": 302.6866194500001, "children": { "TorchPPOOptimizer.update": { "total": 208.3265462510028, "count": 22797, "self": 208.3265462510028 } } } } } } }, "trainer_threads": { "total": 1.1229999472561758e-06, "count": 1, "self": 1.1229999472561758e-06 }, "TrainerController._save_models": { "total": 0.12571591000005355, "count": 1, "self": 0.0019318839999868942, "children": { "RLTrainer._checkpoint": { "total": 0.12378402600006666, "count": 1, "self": 0.12378402600006666 } } } } } } }