{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.29629769921302795, "min": 0.29629769921302795, "max": 1.434989333152771, "count": 52 }, "Pyramids.Policy.Entropy.sum": { "value": 8926.857421875, "min": 8926.857421875, "max": 43531.8359375, "count": 52 }, "Pyramids.Step.mean": { "value": 1559970.0, "min": 29952.0, "max": 1559970.0, "count": 52 }, "Pyramids.Step.sum": { "value": 1559970.0, "min": 29952.0, "max": 1559970.0, "count": 52 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7655596137046814, "min": -0.13056272268295288, "max": 0.8183979988098145, "count": 52 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 224.30897521972656, "min": -31.46561622619629, "max": 244.7010040283203, "count": 52 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.024215348064899445, "min": -0.02556779608130455, "max": 0.18136633932590485, "count": 52 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 7.095097064971924, "min": -6.954440593719482, "max": 43.70928955078125, "count": 52 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06571948163244608, "min": 0.06276143537058185, "max": 0.07355195561339105, "count": 52 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.920072742854245, "min": 0.5013866976171801, "max": 1.062777649970182, "count": 52 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015975412891633775, "min": 0.0007731232815596597, "max": 0.015975412891633775, "count": 52 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22365578048287285, "min": 0.010823725941835236, "max": 0.22365578048287285, "count": 52 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00014546436579760956, "min": 0.00014546436579760956, "max": 0.00029838354339596195, "count": 52 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.002036501121166534, "min": 0.002036501121166534, "max": 0.003969358376880567, "count": 52 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.14848810476190474, "min": 0.14848810476190474, "max": 0.19946118095238097, "count": 52 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.0788334666666666, "min": 1.3962282666666668, "max": 2.7974904333333335, "count": 52 }, "Pyramids.Policy.Beta.mean": { "value": 0.004853961665714285, "min": 0.004853961665714285, "max": 0.009946171977142856, "count": 52 }, "Pyramids.Policy.Beta.sum": { "value": 0.06795546331999999, "min": 0.06795546331999999, "max": 0.13231963139, "count": 52 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007897271774709225, "min": 0.007290591951459646, "max": 0.3831159472465515, "count": 52 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.110561802983284, "min": 0.10324950516223907, "max": 2.681811571121216, "count": 52 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 244.34166666666667, "min": 238.48387096774192, "max": 999.0, "count": 52 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29321.0, "min": 15984.0, "max": 32864.0, "count": 52 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.721847042566588, "min": -1.0000000521540642, "max": 1.7458479885458946, "count": 52 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 204.89979806542397, "min": -30.418201573193073, "max": 218.23099856823683, "count": 52 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.721847042566588, "min": -1.0000000521540642, "max": 1.7458479885458946, "count": 52 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 204.89979806542397, "min": -30.418201573193073, "max": 218.23099856823683, "count": 52 }, "Pyramids.Policy.RndReward.mean": { "value": 0.020187896396328908, "min": 0.018207208109786734, "max": 7.635788524523377, "count": 52 }, "Pyramids.Policy.RndReward.sum": { "value": 2.40235967116314, "min": 2.1894325195462443, "max": 122.17261639237404, "count": 52 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 52 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 52 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1744794236", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1744797953" }, "total": 3717.534661195, "count": 1, "self": 0.5292686880002293, "children": { "run_training.setup": { "total": 0.021541748999993615, "count": 1, "self": 0.021541748999993615 }, "TrainerController.start_learning": { "total": 3716.983850758, "count": 1, "self": 2.2722840548713066, "children": { "TrainerController._reset_env": { "total": 2.3731769139999415, "count": 1, "self": 2.3731769139999415 }, "TrainerController.advance": { "total": 3712.335649773129, "count": 100431, "self": 2.4051787880621305, "children": { "env_step": { "total": 2620.37127809298, "count": 100431, "self": 2367.1822429749063, "children": { "SubprocessEnvManager._take_step": { "total": 251.81755699206371, "count": 100431, "self": 7.672478795943448, "children": { "TorchPolicy.evaluate": { "total": 244.14507819612027, "count": 97595, "self": 244.14507819612027 } } }, "workers": { "total": 1.3714781260099471, "count": 100430, "self": 0.0, "children": { "worker_root": { "total": 3708.966619334976, "count": 100430, "is_parallel": true, "self": 1527.5785602849865, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019996690000425588, "count": 1, "is_parallel": true, "self": 0.0007045720000178335, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012950970000247253, "count": 8, "is_parallel": true, "self": 0.0012950970000247253 } } }, "UnityEnvironment.step": { "total": 0.10107741299998452, "count": 1, "is_parallel": true, "self": 0.0005384649998632085, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005108049999762443, "count": 1, "is_parallel": true, "self": 0.0005108049999762443 }, "communicator.exchange": { "total": 0.09844776600004934, "count": 1, "is_parallel": true, "self": 0.09844776600004934 }, "steps_from_proto": { "total": 0.001580377000095723, "count": 1, "is_parallel": true, "self": 0.00036458200020206277, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012157949998936601, "count": 8, "is_parallel": true, "self": 0.0012157949998936601 } } } } } } }, "UnityEnvironment.step": { "total": 2181.3880590499894, "count": 100429, "is_parallel": true, "self": 50.58178325103381, "children": { "UnityEnvironment._generate_step_input": { "total": 36.86657528801118, "count": 100429, "is_parallel": true, "self": 36.86657528801118 }, "communicator.exchange": { "total": 1938.042021935017, "count": 100429, "is_parallel": true, "self": 1938.042021935017 }, "steps_from_proto": { "total": 155.89767857592722, "count": 100429, "is_parallel": true, "self": 31.934049917978086, "children": { "_process_rank_one_or_two_observation": { "total": 123.96362865794913, "count": 803432, "is_parallel": true, "self": 123.96362865794913 } } } } } } } } } } }, "trainer_advance": { "total": 1089.5591928920867, "count": 100430, "self": 4.623659040079929, "children": { "process_trajectory": { "total": 212.08193389300254, "count": 100430, "self": 211.7908756750021, "children": { "RLTrainer._checkpoint": { "total": 0.29105821800044396, "count": 3, "self": 0.29105821800044396 } } }, "_update_policy": { "total": 872.8535999590041, "count": 716, "self": 480.3764728059965, "children": { "TorchPPOOptimizer.update": { "total": 392.4771271530076, "count": 35604, "self": 392.4771271530076 } } } } } } }, "trainer_threads": { "total": 1.6389994925702922e-06, "count": 1, "self": 1.6389994925702922e-06 }, "TrainerController._save_models": { "total": 0.0027383770002415986, "count": 1, "self": 2.4950000806711614e-05, "children": { "RLTrainer._checkpoint": { "total": 0.002713426999434887, "count": 1, "self": 0.002713426999434887 } } } } } } }