{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.13184496760368347, "min": 0.13184496760368347, "max": 1.4822498559951782, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 3982.77294921875, "min": 3982.77294921875, "max": 44965.53125, "count": 100 }, "Pyramids.Step.mean": { "value": 2999993.0, "min": 29952.0, "max": 2999993.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999993.0, "min": 29952.0, "max": 2999993.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8328659534454346, "min": -0.09728840738534927, "max": 0.8808701038360596, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 248.19406127929688, "min": -23.05735206604004, "max": 273.0697326660156, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.006439580582082272, "min": -0.00407301215454936, "max": 0.29285329580307007, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.9189950227737427, "min": -1.1484415531158447, "max": 70.87049865722656, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06837461225454865, "min": 0.06403398827075892, "max": 0.07411825970727175, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0256191838182298, "min": 0.5053275274656426, "max": 1.0808671761478763, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.012668412985596685, "min": 0.0010548430259821105, "max": 0.01688828859048607, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19002619478395028, "min": 0.013712959337767436, "max": 0.236436040266805, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5065128311955517e-06, "min": 1.5065128311955517e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.2597692467933276e-05, "min": 2.2597692467933276e-05, "max": 0.003969411176862966, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10050213777777778, "min": 0.10050213777777778, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5075320666666667, "min": 1.3962282666666668, "max": 2.7974073666666666, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.016356399999987e-05, "min": 6.016356399999987e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0009024534599999981, "min": 0.0009024534599999981, "max": 0.13232138962999998, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007349861320108175, "min": 0.007349861320108175, "max": 0.40122297406196594, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11024791747331619, "min": 0.10338691622018814, "max": 2.808560848236084, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 218.74615384615385, "min": 203.40268456375838, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28437.0, "min": 15984.0, "max": 33908.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.735083059565379, "min": -1.0000000521540642, "max": 1.7965973037601317, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 225.56079774349928, "min": -27.846001595258713, "max": 267.6929982602596, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.735083059565379, "min": -1.0000000521540642, "max": 1.7965973037601317, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 225.56079774349928, "min": -27.846001595258713, "max": 267.6929982602596, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.01679924415030445, "min": 0.01679924415030445, "max": 7.424902390688658, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1839017395395786, "min": 2.1839017395395786, "max": 118.79843825101852, "count": 100 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718051394", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/candrews/anaconda3/envs/hface/bin/mlagents-learn ../../ml-agents/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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718059697" }, "total": 8303.217881015036, "count": 1, "self": 0.3703381250379607, "children": { "run_training.setup": { "total": 0.019758751965127885, "count": 1, "self": 0.019758751965127885 }, "TrainerController.start_learning": { "total": 8302.827784138033, "count": 1, "self": 4.184830242069438, "children": { "TrainerController._reset_env": { "total": 2.8082355079241097, "count": 1, "self": 2.8082355079241097 }, "TrainerController.advance": { "total": 8295.743851216044, "count": 195750, "self": 3.9444028534926474, "children": { "env_step": { "total": 5533.994430996827, "count": 195750, "self": 4659.066174480249, "children": { "SubprocessEnvManager._take_step": { "total": 872.2133711609058, "count": 195750, "self": 14.693932362133637, "children": { "TorchPolicy.evaluate": { "total": 857.5194387987722, "count": 187568, "self": 857.5194387987722 } } }, "workers": { "total": 2.7148853556718677, "count": 195750, "self": 0.0, "children": { "worker_root": { "total": 8293.506426043808, "count": 195750, "is_parallel": true, "self": 3937.4580739110243, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001349368947558105, "count": 1, "is_parallel": true, "self": 0.000430830055847764, "children": { "_process_rank_one_or_two_observation": { "total": 0.000918538891710341, "count": 8, "is_parallel": true, "self": 0.000918538891710341 } } }, "UnityEnvironment.step": { "total": 0.04484624497126788, "count": 1, "is_parallel": true, "self": 0.0002957609249278903, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003370000049471855, "count": 1, "is_parallel": true, "self": 0.0003370000049471855 }, "communicator.exchange": { "total": 0.04342591401655227, "count": 1, "is_parallel": true, "self": 0.04342591401655227 }, "steps_from_proto": { "total": 0.0007875700248405337, "count": 1, "is_parallel": true, "self": 0.0001849898835644126, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006025801412761211, "count": 8, "is_parallel": true, "self": 0.0006025801412761211 } } } } } } }, "UnityEnvironment.step": { "total": 4356.048352132784, "count": 195749, "is_parallel": true, "self": 63.362619345774874, "children": { "UnityEnvironment._generate_step_input": { "total": 45.78458228788804, "count": 195749, "is_parallel": true, "self": 45.78458228788804 }, "communicator.exchange": { "total": 4064.0104354887735, "count": 195749, "is_parallel": true, "self": 4064.0104354887735 }, "steps_from_proto": { "total": 182.89071501034778, "count": 195749, "is_parallel": true, "self": 40.65266373322811, "children": { "_process_rank_one_or_two_observation": { "total": 142.23805127711967, "count": 1565992, "is_parallel": true, "self": 142.23805127711967 } } } } } } } } } } }, "trainer_advance": { "total": 2757.805017365725, "count": 195750, "self": 8.462788518052548, "children": { "process_trajectory": { "total": 515.4392562208232, "count": 195750, "self": 514.7248824129347, "children": { "RLTrainer._checkpoint": { "total": 0.714373807888478, "count": 6, "self": 0.714373807888478 } } }, "_update_policy": { "total": 2233.902972626849, "count": 1403, "self": 1053.6545168078737, "children": { "TorchPPOOptimizer.update": { "total": 1180.2484558189753, "count": 68376, "self": 1180.2484558189753 } } } } } } }, "trainer_threads": { "total": 6.100162863731384e-07, "count": 1, "self": 6.100162863731384e-07 }, "TrainerController._save_models": { "total": 0.0908665619790554, "count": 1, "self": 0.0009743589907884598, "children": { "RLTrainer._checkpoint": { "total": 0.08989220298826694, "count": 1, "self": 0.08989220298826694 } } } } } } }