{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3544452488422394, "min": 0.3544452488422394, "max": 1.4913043975830078, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10542.619140625, "min": 10542.619140625, "max": 45240.2109375, "count": 33 }, "Pyramids.Step.mean": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989978.0, "min": 29952.0, "max": 989978.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5373697876930237, "min": -0.081179179251194, "max": 0.578998327255249, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 149.3887939453125, "min": -19.56418228149414, "max": 163.27752685546875, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0081275450065732, "min": -0.008483543060719967, "max": 0.28237053751945496, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.259457588195801, "min": -2.3923592567443848, "max": 66.92181396484375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06695057811189649, "min": 0.0640867052596545, "max": 0.0726620946489555, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0042586716784474, "min": 0.49804020635937557, "max": 1.0801007845199337, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.0159011288542792, "min": 0.0011691723704454764, "max": 0.016306910608869254, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23851693281418798, "min": 0.014030068445345717, "max": 0.2446036591330388, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.429277523606666e-06, "min": 7.429277523606666e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001114391628541, "min": 0.0001114391628541, "max": 0.0036346444884519, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247639333333333, "min": 0.10247639333333333, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5371459, "min": 1.3886848, "max": 2.6115481000000003, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025739169400000003, "min": 0.00025739169400000003, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0038608754100000003, "min": 0.0038608754100000003, "max": 0.12117365519, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008611258119344711, "min": 0.008515154011547565, "max": 0.3904452621936798, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12916886806488037, "min": 0.11921215802431107, "max": 2.733116865158081, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 349.4021739130435, "min": 313.11, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32145.0, "min": 15984.0, "max": 33779.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.5857560321033657, "min": -1.0000000521540642, "max": 1.6251128605834328, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 144.30379892140627, "min": -28.492601722478867, "max": 164.13639891892672, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.5857560321033657, "min": -1.0000000521540642, "max": 1.6251128605834328, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 144.30379892140627, "min": -28.492601722478867, "max": 164.13639891892672, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03125652969622304, "min": 0.031067276430876936, "max": 8.253224917687476, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8443442023562966, "min": 2.4394634728960227, "max": 132.0515986829996, "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": "1724334407", "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": "1724336573" }, "total": 2166.205337751, "count": 1, "self": 0.4816504360005638, "children": { "run_training.setup": { "total": 0.05342917000007219, "count": 1, "self": 0.05342917000007219 }, "TrainerController.start_learning": { "total": 2165.6702581449995, "count": 1, "self": 1.3291047469692785, "children": { "TrainerController._reset_env": { "total": 2.176384383000368, "count": 1, "self": 2.176384383000368 }, "TrainerController.advance": { "total": 2162.07973004903, "count": 64029, "self": 1.3666564688683138, "children": { "env_step": { "total": 1525.8116832061537, "count": 64029, "self": 1397.132796635247, "children": { "SubprocessEnvManager._take_step": { "total": 127.90198741091945, "count": 64029, "self": 4.517316489952918, "children": { "TorchPolicy.evaluate": { "total": 123.38467092096653, "count": 62563, "self": 123.38467092096653 } } }, "workers": { "total": 0.7768991599873516, "count": 64029, "self": 0.0, "children": { "worker_root": { "total": 2160.585171317923, "count": 64029, "is_parallel": true, "self": 879.7276145648448, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021918190000178583, "count": 1, "is_parallel": true, "self": 0.0007766990001982776, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014151199998195807, "count": 8, "is_parallel": true, "self": 0.0014151199998195807 } } }, "UnityEnvironment.step": { "total": 0.04982157200038273, "count": 1, "is_parallel": true, "self": 0.0005954490002295643, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005016039999645727, "count": 1, "is_parallel": true, "self": 0.0005016039999645727 }, "communicator.exchange": { "total": 0.04710978000002797, "count": 1, "is_parallel": true, "self": 0.04710978000002797 }, "steps_from_proto": { "total": 0.0016147390001606254, "count": 1, "is_parallel": true, "self": 0.0003391490004105435, "children": { "_process_rank_one_or_two_observation": { "total": 0.001275589999750082, "count": 8, "is_parallel": true, "self": 0.001275589999750082 } } } } } } }, "UnityEnvironment.step": { "total": 1280.8575567530784, "count": 64028, "is_parallel": true, "self": 32.4610638678696, "children": { "UnityEnvironment._generate_step_input": { "total": 22.162669814022593, "count": 64028, "is_parallel": true, "self": 22.162669814022593 }, "communicator.exchange": { "total": 1131.0054106120338, "count": 64028, "is_parallel": true, "self": 1131.0054106120338 }, "steps_from_proto": { "total": 95.22841245915242, "count": 64028, "is_parallel": true, "self": 18.99346975195749, "children": { "_process_rank_one_or_two_observation": { "total": 76.23494270719493, "count": 512224, "is_parallel": true, "self": 76.23494270719493 } } } } } } } } } } }, "trainer_advance": { "total": 634.9013903740079, "count": 64029, "self": 2.6150629210333136, "children": { "process_trajectory": { "total": 125.52293192997104, "count": 64029, "self": 125.32630772097127, "children": { "RLTrainer._checkpoint": { "total": 0.19662420899976496, "count": 2, "self": 0.19662420899976496 } } }, "_update_policy": { "total": 506.7633955230035, "count": 455, "self": 299.93147878598666, "children": { "TorchPPOOptimizer.update": { "total": 206.83191673701685, "count": 22803, "self": 206.83191673701685 } } } } } } }, "trainer_threads": { "total": 8.810002327663824e-07, "count": 1, "self": 8.810002327663824e-07 }, "TrainerController._save_models": { "total": 0.08503808499972365, "count": 1, "self": 0.0013202919990362716, "children": { "RLTrainer._checkpoint": { "total": 0.08371779300068738, "count": 1, "self": 0.08371779300068738 } } } } } } }