{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.32226842641830444, "min": 0.31568917632102966, "max": 1.467311978340149, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 9642.271484375, "min": 9405.01171875, "max": 44512.375, "count": 33 }, "Pyramids.Step.mean": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989908.0, "min": 29952.0, "max": 989908.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5845479369163513, "min": -0.10992363095283508, "max": 0.6119207739830017, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 164.25796508789062, "min": -26.491594314575195, "max": 173.173583984375, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.013636847026646137, "min": 0.0005816722405143082, "max": 0.390365332365036, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 3.831954002380371, "min": 0.15763317048549652, "max": 92.51658630371094, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07060504017431349, "min": 0.06307097985769533, "max": 0.07373208884113594, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9884705624403889, "min": 0.4831312829802541, "max": 1.0614909251961246, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016946609919425752, "min": 0.00018758033855427355, "max": 0.01716063552824174, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23725253887196052, "min": 0.002438544401205556, "max": 0.2518033171751692, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.5688189056642845e-06, "min": 7.5688189056642845e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010596346467929998, "min": 0.00010596346467929998, "max": 0.0034931092356303, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252290714285715, "min": 0.10252290714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4353207000000001, "min": 1.3691136000000002, "max": 2.5273428, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002620384235714285, "min": 0.0002620384235714285, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036685379299999992, "min": 0.0036685379299999992, "max": 0.11645053303, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011940359137952328, "min": 0.01166471280157566, "max": 0.3948514759540558, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16716502606868744, "min": 0.16330598294734955, "max": 2.763960361480713, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 308.7319587628866, "min": 308.7319587628866, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29947.0, "min": 15984.0, "max": 32442.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6293896733178306, "min": -1.0000000521540642, "max": 1.650310329493435, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 158.05079831182957, "min": -32.000001668930054, "max": 164.04279805719852, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6293896733178306, "min": -1.0000000521540642, "max": 1.650310329493435, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 158.05079831182957, "min": -32.000001668930054, "max": 164.04279805719852, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.038300036837961335, "min": 0.038300036837961335, "max": 8.445369634777308, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.7151035732822493, "min": 3.6696670920064207, "max": 135.12591415643692, "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": "1761023298", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.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": "1761026587" }, "total": 3289.210565798, "count": 1, "self": 0.9897551349999958, "children": { "run_training.setup": { "total": 0.0412962030000017, "count": 1, "self": 0.0412962030000017 }, "TrainerController.start_learning": { "total": 3288.17951446, "count": 1, "self": 2.349728810037959, "children": { "TrainerController._reset_env": { "total": 2.87448349400006, "count": 1, "self": 2.87448349400006 }, "TrainerController.advance": { "total": 3282.777234347963, "count": 63978, "self": 2.4442705508390645, "children": { "env_step": { "total": 2256.4561598990986, "count": 63978, "self": 2100.434348110026, "children": { "SubprocessEnvManager._take_step": { "total": 154.6542078580228, "count": 63978, "self": 6.755194836061719, "children": { "TorchPolicy.evaluate": { "total": 147.89901302196108, "count": 62564, "self": 147.89901302196108 } } }, "workers": { "total": 1.3676039310496435, "count": 63978, "self": 0.0, "children": { "worker_root": { "total": 3279.46192466307, "count": 63978, "is_parallel": true, "self": 1357.5903207420467, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0041850869999962015, "count": 1, "is_parallel": true, "self": 0.0015199950000805984, "children": { "_process_rank_one_or_two_observation": { "total": 0.002665091999915603, "count": 8, "is_parallel": true, "self": 0.002665091999915603 } } }, "UnityEnvironment.step": { "total": 0.08283028699997885, "count": 1, "is_parallel": true, "self": 0.0006554660001256707, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005346959999315004, "count": 1, "is_parallel": true, "self": 0.0005346959999315004 }, "communicator.exchange": { "total": 0.07963455300000533, "count": 1, "is_parallel": true, "self": 0.07963455300000533 }, "steps_from_proto": { "total": 0.0020055719999163557, "count": 1, "is_parallel": true, "self": 0.00042548399960651295, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015800880003098428, "count": 8, "is_parallel": true, "self": 0.0015800880003098428 } } } } } } }, "UnityEnvironment.step": { "total": 1921.8716039210233, "count": 63977, "is_parallel": true, "self": 45.71792260100642, "children": { "UnityEnvironment._generate_step_input": { "total": 30.4311928510931, "count": 63977, "is_parallel": true, "self": 30.4311928510931 }, "communicator.exchange": { "total": 1701.6997588389677, "count": 63977, "is_parallel": true, "self": 1701.6997588389677 }, "steps_from_proto": { "total": 144.02272962995607, "count": 63977, "is_parallel": true, "self": 29.085989087926464, "children": { "_process_rank_one_or_two_observation": { "total": 114.93674054202961, "count": 511816, "is_parallel": true, "self": 114.93674054202961 } } } } } } } } } } }, "trainer_advance": { "total": 1023.876803898025, "count": 63978, "self": 4.381058182013476, "children": { "process_trajectory": { "total": 155.77158011401616, "count": 63978, "self": 155.51585146201614, "children": { "RLTrainer._checkpoint": { "total": 0.25572865200001615, "count": 2, "self": 0.25572865200001615 } } }, "_update_policy": { "total": 863.7241656019953, "count": 448, "self": 349.4400467539747, "children": { "TorchPPOOptimizer.update": { "total": 514.2841188480206, "count": 22785, "self": 514.2841188480206 } } } } } } }, "trainer_threads": { "total": 1.3869994290871546e-06, "count": 1, "self": 1.3869994290871546e-06 }, "TrainerController._save_models": { "total": 0.17806642100003955, "count": 1, "self": 0.0072108180002032896, "children": { "RLTrainer._checkpoint": { "total": 0.17085560299983626, "count": 1, "self": 0.17085560299983626 } } } } } } }