{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5477709770202637, "min": 0.5477709770202637, "max": 1.5376756191253662, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16406.8359375, "min": 16406.8359375, "max": 46646.92578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989931.0, "min": 29952.0, "max": 989931.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.29183682799339294, "min": -0.0991879478096962, "max": 0.29670780897140503, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 75.58573913574219, "min": -23.904294967651367, "max": 75.58573913574219, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.017762236297130585, "min": -0.00010093615128425881, "max": 0.1918834149837494, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.600419044494629, "min": -0.026142463088035583, "max": 46.05202102661133, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07227792515533067, "min": 0.0661652494568268, "max": 0.07299653024928864, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0118909521746293, "min": 0.4763360167244695, "max": 1.0506457318842877, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01222613993048158, "min": 0.0007219597523477356, "max": 0.01222613993048158, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.17116595902674211, "min": 0.008663517028172828, "max": 0.17999550926469965, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4307332374071425e-06, "min": 7.4307332374071425e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001040302653237, "min": 0.0001040302653237, "max": 0.003138944653685201, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10247687857142858, "min": 0.10247687857142858, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4346763, "min": 1.3691136000000002, "max": 2.3598660000000002, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025744016928571435, "min": 0.00025744016928571435, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003604162370000001, "min": 0.003604162370000001, "max": 0.10465684852, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01292400248348713, "min": 0.01292400248348713, "max": 0.3447401821613312, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1809360384941101, "min": 0.1809360384941101, "max": 2.4131813049316406, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 555.0, "min": 555.0, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 15984.0, "max": 34161.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.1856777480355016, "min": -1.0000000521540642, "max": 1.1856777480355016, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 64.02659839391708, "min": -32.000001668930054, "max": 64.02659839391708, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.1856777480355016, "min": -1.0000000521540642, "max": 1.1856777480355016, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 64.02659839391708, "min": -32.000001668930054, "max": 64.02659839391708, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.07492339191095973, "min": 0.07492339191095973, "max": 6.647942203097045, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.045863163191825, "min": 3.9683152755897027, "max": 106.36707524955273, "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": "1680180810", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1680182796" }, "total": 1986.4149166280001, "count": 1, "self": 0.47715537599992786, "children": { "run_training.setup": { "total": 0.1870303050000075, "count": 1, "self": 0.1870303050000075 }, "TrainerController.start_learning": { "total": 1985.7507309470002, "count": 1, "self": 1.379242777996069, "children": { "TrainerController._reset_env": { "total": 5.842450038999914, "count": 1, "self": 5.842450038999914 }, "TrainerController.advance": { "total": 1978.4348472010042, "count": 63358, "self": 1.5002888700755648, "children": { "env_step": { "total": 1363.8221432159824, "count": 63358, "self": 1254.410043038995, "children": { "SubprocessEnvManager._take_step": { "total": 108.56436640500465, "count": 63358, "self": 4.688178025071693, "children": { "TorchPolicy.evaluate": { "total": 103.87618837993296, "count": 62567, "self": 103.87618837993296 } } }, "workers": { "total": 0.8477337719828029, "count": 63358, "self": 0.0, "children": { "worker_root": { "total": 1981.227582263926, "count": 63358, "is_parallel": true, "self": 842.870110100919, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018300470001122449, "count": 1, "is_parallel": true, "self": 0.0006856500001504173, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011443969999618275, "count": 8, "is_parallel": true, "self": 0.0011443969999618275 } } }, "UnityEnvironment.step": { "total": 0.050706957999864244, "count": 1, "is_parallel": true, "self": 0.0005358259998047288, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005847190000167757, "count": 1, "is_parallel": true, "self": 0.0005847190000167757 }, "communicator.exchange": { "total": 0.04773808699997062, "count": 1, "is_parallel": true, "self": 0.04773808699997062 }, "steps_from_proto": { "total": 0.0018483260000721202, "count": 1, "is_parallel": true, "self": 0.00039506300026914687, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014532629998029734, "count": 8, "is_parallel": true, "self": 0.0014532629998029734 } } } } } } }, "UnityEnvironment.step": { "total": 1138.357472163007, "count": 63357, "is_parallel": true, "self": 30.899729625932878, "children": { "UnityEnvironment._generate_step_input": { "total": 23.499613193022697, "count": 63357, "is_parallel": true, "self": 23.499613193022697 }, "communicator.exchange": { "total": 990.9931998060329, "count": 63357, "is_parallel": true, "self": 990.9931998060329 }, "steps_from_proto": { "total": 92.96492953801862, "count": 63357, "is_parallel": true, "self": 20.058824806999382, "children": { "_process_rank_one_or_two_observation": { "total": 72.90610473101924, "count": 506856, "is_parallel": true, "self": 72.90610473101924 } } } } } } } } } } }, "trainer_advance": { "total": 613.1124151149463, "count": 63358, "self": 2.426378792959895, "children": { "process_trajectory": { "total": 118.15689903998509, "count": 63358, "self": 117.95734064398539, "children": { "RLTrainer._checkpoint": { "total": 0.19955839599970204, "count": 2, "self": 0.19955839599970204 } } }, "_update_policy": { "total": 492.52913728200133, "count": 438, "self": 312.4164636300268, "children": { "TorchPPOOptimizer.update": { "total": 180.11267365197455, "count": 22863, "self": 180.11267365197455 } } } } } } }, "trainer_threads": { "total": 1.0369999472459313e-06, "count": 1, "self": 1.0369999472459313e-06 }, "TrainerController._save_models": { "total": 0.09418989200003125, "count": 1, "self": 0.0018274569997629442, "children": { "RLTrainer._checkpoint": { "total": 0.0923624350002683, "count": 1, "self": 0.0923624350002683 } } } } } } }