{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3343666195869446, "min": 0.3315838873386383, "max": 1.5349911451339722, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10025.6484375, "min": 9926.294921875, "max": 46565.4921875, "count": 33 }, "Pyramids.Step.mean": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989898.0, "min": 29952.0, "max": 989898.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6206203699111938, "min": -0.09521139413118362, "max": 0.6206203699111938, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 176.87680053710938, "min": -22.945945739746094, "max": 176.87680053710938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.022684117779135704, "min": -0.010490518063306808, "max": 0.22063514590263367, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 6.464973449707031, "min": -2.9058735370635986, "max": 53.17306900024414, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06974616629361431, "min": 0.06576323083746026, "max": 0.07242925686284407, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9764463281106003, "min": 0.48667176288549907, "max": 1.0616992208233567, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.017749954372903994, "min": 0.0011525672247774544, "max": 0.017892887284137904, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.2484993612206559, "min": 0.012282580682395568, "max": 0.25050042197793065, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.563354621771429e-06, "min": 7.563354621771429e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010588696470480001, "min": 0.00010588696470480001, "max": 0.0036328555890482, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10252108571428573, "min": 0.10252108571428573, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4352952, "min": 1.3886848, "max": 2.610951800000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002618564628571429, "min": 0.0002618564628571429, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036659904800000007, "min": 0.0036659904800000007, "max": 0.12111408482000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011527402326464653, "min": 0.011509081348776817, "max": 0.3488496243953705, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.16138362884521484, "min": 0.16138362884521484, "max": 2.4419474601745605, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 284.0095238095238, "min": 284.0095238095238, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29821.0, "min": 15984.0, "max": 33818.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6969390362501144, "min": -1.0000000521540642, "max": 1.6969390362501144, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 178.17859880626202, "min": -30.545001685619354, "max": 178.17859880626202, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6969390362501144, "min": -1.0000000521540642, "max": 1.6969390362501144, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 178.17859880626202, "min": -30.545001685619354, "max": 178.17859880626202, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0339783094346612, "min": 0.0339783094346612, "max": 6.748974781483412, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.567722490639426, "min": 3.542429917026311, "max": 107.98359650373459, "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": "1675143944", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1675146315" }, "total": 2370.796157995, "count": 1, "self": 0.5260244849996525, "children": { "run_training.setup": { "total": 0.11609115100009149, "count": 1, "self": 0.11609115100009149 }, "TrainerController.start_learning": { "total": 2370.1540423590004, "count": 1, "self": 1.6417791239719008, "children": { "TrainerController._reset_env": { "total": 6.733916017000183, "count": 1, "self": 6.733916017000183 }, "TrainerController.advance": { "total": 2361.6891176730282, "count": 64062, "self": 1.816082399021525, "children": { "env_step": { "total": 1643.4242629030564, "count": 64062, "self": 1515.6528146241121, "children": { "SubprocessEnvManager._take_step": { "total": 126.7465977419613, "count": 64062, "self": 5.0714817829364165, "children": { "TorchPolicy.evaluate": { "total": 121.67511595902488, "count": 62565, "self": 41.06914105795363, "children": { "TorchPolicy.sample_actions": { "total": 80.60597490107125, "count": 62565, "self": 80.60597490107125 } } } } }, "workers": { "total": 1.0248505369829672, "count": 64062, "self": 0.0, "children": { "worker_root": { "total": 2364.0058192290453, "count": 64062, "is_parallel": true, "self": 969.6605321060435, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002089614999931655, "count": 1, "is_parallel": true, "self": 0.0007251909999013151, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013644240000303398, "count": 8, "is_parallel": true, "self": 0.0013644240000303398 } } }, "UnityEnvironment.step": { "total": 0.048523368000132905, "count": 1, "is_parallel": true, "self": 0.0005847260003974952, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004597579998062429, "count": 1, "is_parallel": true, "self": 0.0004597579998062429 }, "communicator.exchange": { "total": 0.0457099919999564, "count": 1, "is_parallel": true, "self": 0.0457099919999564 }, "steps_from_proto": { "total": 0.001768891999972766, "count": 1, "is_parallel": true, "self": 0.0004385619995446177, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013303300004281482, "count": 8, "is_parallel": true, "self": 0.0013303300004281482 } } } } } } }, "UnityEnvironment.step": { "total": 1394.3452871230018, "count": 64061, "is_parallel": true, "self": 32.41118138408228, "children": { "UnityEnvironment._generate_step_input": { "total": 24.929513161935347, "count": 64061, "is_parallel": true, "self": 24.929513161935347 }, "communicator.exchange": { "total": 1225.9925082049995, "count": 64061, "is_parallel": true, "self": 1225.9925082049995 }, "steps_from_proto": { "total": 111.01208437198466, "count": 64061, "is_parallel": true, "self": 26.647474751079017, "children": { "_process_rank_one_or_two_observation": { "total": 84.36460962090564, "count": 512488, "is_parallel": true, "self": 84.36460962090564 } } } } } } } } } } }, "trainer_advance": { "total": 716.4487723709503, "count": 64062, "self": 3.1374298359494333, "children": { "process_trajectory": { "total": 156.7305548469992, "count": 64062, "self": 156.52643831799946, "children": { "RLTrainer._checkpoint": { "total": 0.20411652899974797, "count": 2, "self": 0.20411652899974797 } } }, "_update_policy": { "total": 556.5807876880017, "count": 453, "self": 202.68425045203549, "children": { "TorchPPOOptimizer.update": { "total": 353.8965372359662, "count": 22821, "self": 353.8965372359662 } } } } } } }, "trainer_threads": { "total": 1.05399976746412e-06, "count": 1, "self": 1.05399976746412e-06 }, "TrainerController._save_models": { "total": 0.08922849100054009, "count": 1, "self": 0.0015261270009432337, "children": { "RLTrainer._checkpoint": { "total": 0.08770236399959686, "count": 1, "self": 0.08770236399959686 } } } } } } }