{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2891353964805603, "min": 0.2686712443828583, "max": 1.5281963348388672, "count": 48 }, "Pyramids.Policy.Entropy.sum": { "value": 8627.7998046875, "min": 7969.86376953125, "max": 46359.36328125, "count": 48 }, "Pyramids.Step.mean": { "value": 1439917.0, "min": 29952.0, "max": 1439917.0, "count": 48 }, "Pyramids.Step.sum": { "value": 1439917.0, "min": 29952.0, "max": 1439917.0, "count": 48 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6851173639297485, "min": -0.12503549456596375, "max": 0.6851173639297485, "count": 48 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 195.25845336914062, "min": -30.008520126342773, "max": 196.00906372070312, "count": 48 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004011654295027256, "min": -0.04039505869150162, "max": 0.20674282312393188, "count": 48 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 1.1433215141296387, "min": -11.027851104736328, "max": 49.61827850341797, "count": 48 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06730560409570378, "min": 0.0653948506106168, "max": 0.07401461382073143, "count": 48 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.942278457339853, "min": 0.48793929248537077, "max": 1.1102192073109716, "count": 48 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014771442195134503, "min": 0.0006933438147003336, "max": 0.014915943164033562, "count": 48 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20680019073188305, "min": 0.008277331227681579, "max": 0.20882320429646986, "count": 48 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00015742698323864047, "min": 0.00015742698323864047, "max": 0.00029838354339596195, "count": 48 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0022039777653409666, "min": 0.0020691136102954665, "max": 0.004027800257399967, "count": 48 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.15247564523809526, "min": 0.15247564523809526, "max": 0.19946118095238097, "count": 48 }, "Pyramids.Policy.Epsilon.sum": { "value": 2.1346590333333335, "min": 1.3897045333333333, "max": 2.842600033333333, "count": 48 }, "Pyramids.Policy.Beta.mean": { "value": 0.005252316959285713, "min": 0.005252316959285713, "max": 0.009946171977142856, "count": 48 }, "Pyramids.Policy.Beta.sum": { "value": 0.07353243742999999, "min": 0.06897148288, "max": 0.13427574333000003, "count": 48 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007949723862111568, "min": 0.007572929374873638, "max": 0.303242951631546, "count": 48 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1112961396574974, "min": 0.10602100938558578, "max": 2.1227006912231445, "count": 48 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 276.6454545454545, "min": 276.6454545454545, "max": 999.0, "count": 48 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30431.0, "min": 15984.0, "max": 33430.0, "count": 48 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7061054384166545, "min": -1.0000000521540642, "max": 1.7061054384166545, "count": 48 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 187.67159822583199, "min": -32.000001668930054, "max": 187.67159822583199, "count": 48 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7061054384166545, "min": -1.0000000521540642, "max": 1.7061054384166545, "count": 48 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 187.67159822583199, "min": -32.000001668930054, "max": 187.67159822583199, "count": 48 }, "Pyramids.Policy.RndReward.mean": { "value": 0.022763607746244155, "min": 0.022763607746244155, "max": 6.167580144479871, "count": 48 }, "Pyramids.Policy.RndReward.sum": { "value": 2.503996852086857, "min": 2.251664378331043, "max": 98.68128231167793, "count": 48 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 48 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 48 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1790092775", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1790096403" }, "total": 3628.08302584, "count": 1, "self": 0.4138266929994643, "children": { "run_training.setup": { "total": 0.025919483000052423, "count": 1, "self": 0.025919483000052423 }, "TrainerController.start_learning": { "total": 3627.6432796640006, "count": 1, "self": 2.291651672066564, "children": { "TrainerController._reset_env": { "total": 2.299523592999776, "count": 1, "self": 2.299523592999776 }, "TrainerController.advance": { "total": 3622.8361625809343, "count": 92761, "self": 2.355793228692619, "children": { "env_step": { "total": 2689.8663726731243, "count": 92761, "self": 2454.481069564104, "children": { "SubprocessEnvManager._take_step": { "total": 234.00178771107358, "count": 92761, "self": 7.271866286081604, "children": { "TorchPolicy.evaluate": { "total": 226.72992142499197, "count": 90684, "self": 226.72992142499197 } } }, "workers": { "total": 1.3835153979466668, "count": 92760, "self": 0.0, "children": { "worker_root": { "total": 3618.987460146066, "count": 92760, "is_parallel": true, "self": 1351.2452391030038, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020015939999211696, "count": 1, "is_parallel": true, "self": 0.0006596380003429658, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013419559995782038, "count": 8, "is_parallel": true, "self": 0.0013419559995782038 } } }, "UnityEnvironment.step": { "total": 0.13000552599987714, "count": 1, "is_parallel": true, "self": 0.0005914039998060616, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004405839999890304, "count": 1, "is_parallel": true, "self": 0.0004405839999890304 }, "communicator.exchange": { "total": 0.12306657199997062, "count": 1, "is_parallel": true, "self": 0.12306657199997062 }, "steps_from_proto": { "total": 0.005906966000111424, "count": 1, "is_parallel": true, "self": 0.004452026999388181, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014549390007232432, "count": 8, "is_parallel": true, "self": 0.0014549390007232432 } } } } } } }, "UnityEnvironment.step": { "total": 2267.7422210430623, "count": 92759, "is_parallel": true, "self": 52.15231539921615, "children": { "UnityEnvironment._generate_step_input": { "total": 36.05676063998271, "count": 92759, "is_parallel": true, "self": 36.05676063998271 }, "communicator.exchange": { "total": 2009.8673741518783, "count": 92759, "is_parallel": true, "self": 2009.8673741518783 }, "steps_from_proto": { "total": 169.66577085198514, "count": 92759, "is_parallel": true, "self": 35.36324630746094, "children": { "_process_rank_one_or_two_observation": { "total": 134.3025245445242, "count": 742072, "is_parallel": true, "self": 134.3025245445242 } } } } } } } } } } }, "trainer_advance": { "total": 930.6139966791175, "count": 92760, "self": 4.357565976064961, "children": { "process_trajectory": { "total": 166.95224301204962, "count": 92760, "self": 166.75485704304992, "children": { "RLTrainer._checkpoint": { "total": 0.19738596899969707, "count": 2, "self": 0.19738596899969707 } } }, "_update_policy": { "total": 759.3041876910029, "count": 658, "self": 409.41607193301843, "children": { "TorchPPOOptimizer.update": { "total": 349.88811575798445, "count": 33066, "self": 349.88811575798445 } } } } } } }, "trainer_threads": { "total": 1.3589997251983732e-06, "count": 1, "self": 1.3589997251983732e-06 }, "TrainerController._save_models": { "total": 0.2159404590001941, "count": 1, "self": 0.002897381999900972, "children": { "RLTrainer._checkpoint": { "total": 0.21304307700029312, "count": 1, "self": 0.21304307700029312 } } } } } } }