{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3781135678291321, "min": 0.3781135678291321, "max": 1.4307013750076294, "count": 41 }, "Pyramids.Policy.Entropy.sum": { "value": 11409.955078125, "min": 11409.955078125, "max": 43401.7578125, "count": 41 }, "Pyramids.Step.mean": { "value": 1229913.0, "min": 29952.0, "max": 1229913.0, "count": 41 }, "Pyramids.Step.sum": { "value": 1229913.0, "min": 29952.0, "max": 1229913.0, "count": 41 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6381216049194336, "min": -0.10954690724611282, "max": 0.6996257305145264, "count": 41 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 179.95028686523438, "min": -26.291257858276367, "max": 197.99407958984375, "count": 41 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.007804469671100378, "min": -0.024467280134558678, "max": 0.379982054233551, "count": 41 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -2.2008605003356934, "min": -6.679567337036133, "max": 91.19569396972656, "count": 41 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06792121414077716, "min": 0.06460621190905971, "max": 0.07395365576528656, "count": 41 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9508969979708803, "min": 0.4869719651820748, "max": 1.0558458053856157, "count": 41 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013743468947840348, "min": 0.00025126062269508457, "max": 0.013744519731896953, "count": 41 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19240856526976488, "min": 0.003015127472341015, "max": 0.19854017142400457, "count": 41 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00017849141193144758, "min": 0.00017849141193144758, "max": 0.00029838354339596195, "count": 41 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0024988797670402662, "min": 0.0020691136102954665, "max": 0.003969489576836833, "count": 41 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.15949712380952383, "min": 0.15949712380952383, "max": 0.19946118095238097, "count": 41 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.2329597333333338, "min": 1.3897045333333333, "max": 2.7825489, "count": 41 }, "Pyramids.Policy.Beta.mean": { "value": 0.005953762668571429, "min": 0.005953762668571429, "max": 0.009946171977142856, "count": 41 }, "Pyramids.Policy.Beta.sum": { "value": 0.08335267736, "min": 0.06897148288, "max": 0.13232400035, "count": 41 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.006227504927664995, "min": 0.006227504927664995, "max": 0.5055810809135437, "count": 41 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.08718506991863251, "min": 0.08718506991863251, "max": 3.5390677452087402, "count": 41 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 294.3679245283019, "min": 294.3679245283019, "max": 999.0, "count": 41 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 31203.0, "min": 15984.0, "max": 32139.0, "count": 41 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6678829978237737, "min": -1.0000000521540642, "max": 1.6784164721203834, "count": 41 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 176.79559776932, "min": -32.000001668930054, "max": 176.79559776932, "count": 41 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6678829978237737, "min": -1.0000000521540642, "max": 1.6784164721203834, "count": 41 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 176.79559776932, "min": -32.000001668930054, "max": 176.79559776932, "count": 41 }, "Pyramids.Policy.RndReward.mean": { "value": 0.019061806392751606, "min": 0.019061806392751606, "max": 9.910126306116581, "count": 41 }, "Pyramids.Policy.RndReward.sum": { "value": 2.0205514776316704, "min": 1.9438937461018213, "max": 158.5620208978653, "count": 41 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 41 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 41 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1719478457", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1719481281" }, "total": 2824.4943215430003, "count": 1, "self": 0.5522601980010222, "children": { "run_training.setup": { "total": 0.05328816699989147, "count": 1, "self": 0.05328816699989147 }, "TrainerController.start_learning": { "total": 2823.8887731779996, "count": 1, "self": 1.817783254080041, "children": { "TrainerController._reset_env": { "total": 2.5952947089999725, "count": 1, "self": 2.5952947089999725 }, "TrainerController.advance": { "total": 2819.3444933879196, "count": 78810, "self": 1.7989594930245403, "children": { "env_step": { "total": 2037.9183940529354, "count": 78810, "self": 1867.8794562079274, "children": { "SubprocessEnvManager._take_step": { "total": 168.9795233120285, "count": 78810, "self": 5.889936549074491, "children": { "TorchPolicy.evaluate": { "total": 163.089586762954, "count": 76980, "self": 163.089586762954 } } }, "workers": { "total": 1.0594145329794173, "count": 78809, "self": 0.0, "children": { "worker_root": { "total": 2817.0680204399755, "count": 78809, "is_parallel": true, "self": 1106.474099785943, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020282610000776913, "count": 1, "is_parallel": true, "self": 0.0005942040002082649, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014340569998694264, "count": 8, "is_parallel": true, "self": 0.0014340569998694264 } } }, "UnityEnvironment.step": { "total": 0.06506225999987691, "count": 1, "is_parallel": true, "self": 0.0006208469999364752, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046270400002867973, "count": 1, "is_parallel": true, "self": 0.00046270400002867973 }, "communicator.exchange": { "total": 0.062499590000015814, "count": 1, "is_parallel": true, "self": 0.062499590000015814 }, "steps_from_proto": { "total": 0.0014791189998959453, "count": 1, "is_parallel": true, "self": 0.000305437000179154, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011736819997167913, "count": 8, "is_parallel": true, "self": 0.0011736819997167913 } } } } } } }, "UnityEnvironment.step": { "total": 1710.5939206540324, "count": 78808, "is_parallel": true, "self": 42.12445150104895, "children": { "UnityEnvironment._generate_step_input": { "total": 29.185929454960842, "count": 78808, "is_parallel": true, "self": 29.185929454960842 }, "communicator.exchange": { "total": 1514.2816479239737, "count": 78808, "is_parallel": true, "self": 1514.2816479239737 }, "steps_from_proto": { "total": 125.001891774049, "count": 78808, "is_parallel": true, "self": 26.01018322192772, "children": { "_process_rank_one_or_two_observation": { "total": 98.99170855212128, "count": 630464, "is_parallel": true, "self": 98.99170855212128 } } } } } } } } } } }, "trainer_advance": { "total": 779.6271398419594, "count": 78809, "self": 3.4709116989604354, "children": { "process_trajectory": { "total": 158.66475321699522, "count": 78809, "self": 158.45334494299482, "children": { "RLTrainer._checkpoint": { "total": 0.21140827400040507, "count": 2, "self": 0.21140827400040507 } } }, "_update_policy": { "total": 617.4914749260038, "count": 560, "self": 364.7966669789571, "children": { "TorchPPOOptimizer.update": { "total": 252.69480794704668, "count": 28074, "self": 252.69480794704668 } } } } } } }, "trainer_threads": { "total": 1.669000084802974e-06, "count": 1, "self": 1.669000084802974e-06 }, "TrainerController._save_models": { "total": 0.131200157999956, "count": 1, "self": 0.002073921000373957, "children": { "RLTrainer._checkpoint": { "total": 0.12912623699958203, "count": 1, "self": 0.12912623699958203 } } } } } } }