{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2477802038192749, "min": 0.2477802038192749, "max": 1.198297142982483, "count": 10 }, "Pyramids.Policy.Entropy.sum": { "value": 24881.09765625, "min": 24881.09765625, "max": 121075.9453125, "count": 10 }, "Pyramids.Step.mean": { "value": 999999.0, "min": 99940.0, "max": 999999.0, "count": 10 }, "Pyramids.Step.sum": { "value": 999999.0, "min": 99940.0, "max": 999999.0, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7147039771080017, "min": -0.07854399085044861, "max": 0.7147039771080017, "count": 10 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 693.2628784179688, "min": -62.913734436035156, "max": 693.2628784179688, "count": 10 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.004759666975587606, "min": 0.004759666975587606, "max": 0.16755923628807068, "count": 10 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.61687707901001, "min": 4.61687707901001, "max": 134.21495056152344, "count": 10 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06787582993881643, "min": 0.06761944514100893, "max": 0.07074977475423962, "count": 10 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 3.190164007124372, "min": 2.3145590704240355, "max": 3.3252394134492618, "count": 10 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016432590551717977, "min": 0.003000186348683012, "max": 0.01643542791269682, "count": 10 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.7723317559307449, "min": 0.10901664588020324, "max": 0.7889005398094473, "count": 10 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.4894303545902132e-05, "min": 1.4894303545902132e-05, "max": 0.00028258485580504993, "count": 10 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0007000322666574002, "min": 0.0007000322666574002, "max": 0.0114570555809817, "count": 10 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10496473617021276, "min": 0.10496473617021276, "max": 0.19419495000000003, "count": 10 }, "Pyramids.Policy.Epsilon.sum": { "value": 4.9333426, "min": 4.9333426, "max": 8.319018300000002, "count": 10 }, "Pyramids.Policy.Beta.mean": { "value": 0.0005059771434042554, "min": 0.0005059771434042554, "max": 0.009420075505, "count": 10 }, "Pyramids.Policy.Beta.sum": { "value": 0.023780925740000004, "min": 0.023780925740000004, "max": 0.38196992817000003, "count": 10 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.011233018711209297, "min": 0.011233018711209297, "max": 0.14837764203548431, "count": 10 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.5279518961906433, "min": 0.5279518961906433, "max": 5.044839859008789, "count": 10 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 260.4255874673629, "min": 260.4255874673629, "max": 971.2474226804123, "count": 10 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 99743.0, "min": 94211.0, "max": 102016.0, "count": 10 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7082339294702205, "min": -0.8278392252233839, "max": 1.7082339294702205, "count": 10 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 654.2535949870944, "min": -80.30040484666824, "max": 654.2535949870944, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7082339294702205, "min": -0.8278392252233839, "max": 1.7082339294702205, "count": 10 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 654.2535949870944, "min": -80.30040484666824, "max": 654.2535949870944, "count": 10 }, "Pyramids.Policy.RndReward.mean": { "value": 0.030350130677334757, "min": 0.030350130677334757, "max": 2.136482576772417, "count": 10 }, "Pyramids.Policy.RndReward.sum": { "value": 11.624100049419212, "min": 11.624100049419212, "max": 207.23880994692445, "count": 10 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1757590521", "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]", "command_line_arguments": "/content/ml-agents/ml-agents/mlagents/trainers/learn.py ./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": "1757592789" }, "total": 2267.9376680610003, "count": 1, "self": 0.7457191359999342, "children": { "run_training.setup": { "total": 0.021787840000115466, "count": 1, "self": 0.021787840000115466 }, "TrainerController.start_learning": { "total": 2267.170161085, "count": 1, "self": 1.4360080889614437, "children": { "TrainerController._reset_env": { "total": 3.488679671, "count": 1, "self": 3.488679671 }, "TrainerController.advance": { "total": 2262.134896374039, "count": 64479, "self": 1.4342535891037187, "children": { "env_step": { "total": 1601.0154606599122, "count": 64479, "self": 1453.5557545327952, "children": { "SubprocessEnvManager._take_step": { "total": 146.5621623310651, "count": 64479, "self": 4.537672662032946, "children": { "TorchPolicy.evaluate": { "total": 142.02448966903216, "count": 62572, "self": 142.02448966903216 } } }, "workers": { "total": 0.8975437960518775, "count": 64479, "self": 0.0, "children": { "worker_root": { "total": 2262.260050544016, "count": 64479, "is_parallel": true, "self": 921.5861958450482, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005255992000002152, "count": 1, "is_parallel": true, "self": 0.003894787000035649, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013612049999665032, "count": 8, "is_parallel": true, "self": 0.0013612049999665032 } } }, "UnityEnvironment.step": { "total": 0.04675529399992229, "count": 1, "is_parallel": true, "self": 0.0005265949996555719, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004867730001478776, "count": 1, "is_parallel": true, "self": 0.0004867730001478776 }, "communicator.exchange": { "total": 0.044177702000069985, "count": 1, "is_parallel": true, "self": 0.044177702000069985 }, "steps_from_proto": { "total": 0.0015642240000488528, "count": 1, "is_parallel": true, "self": 0.00035676299989972904, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012074610001491237, "count": 8, "is_parallel": true, "self": 0.0012074610001491237 } } } } } } }, "UnityEnvironment.step": { "total": 1340.6738546989677, "count": 64478, "is_parallel": true, "self": 32.226898124881245, "children": { "UnityEnvironment._generate_step_input": { "total": 22.925290935039584, "count": 64478, "is_parallel": true, "self": 22.925290935039584 }, "communicator.exchange": { "total": 1190.9763675000474, "count": 64478, "is_parallel": true, "self": 1190.9763675000474 }, "steps_from_proto": { "total": 94.54529813899944, "count": 64478, "is_parallel": true, "self": 19.04819369209804, "children": { "_process_rank_one_or_two_observation": { "total": 75.4971044469014, "count": 515824, "is_parallel": true, "self": 75.4971044469014 } } } } } } } } } } }, "trainer_advance": { "total": 659.685182125023, "count": 64479, "self": 2.835333241055423, "children": { "process_trajectory": { "total": 126.63365237496237, "count": 64479, "self": 126.39205500396201, "children": { "RLTrainer._checkpoint": { "total": 0.24159737100035272, "count": 2, "self": 0.24159737100035272 } } }, "_update_policy": { "total": 530.2161965090052, "count": 457, "self": 295.2357716540225, "children": { "TorchPPOOptimizer.update": { "total": 234.98042485498263, "count": 22803, "self": 234.98042485498263 } } } } } } }, "trainer_threads": { "total": 1.3409999155555852e-06, "count": 1, "self": 1.3409999155555852e-06 }, "TrainerController._save_models": { "total": 0.11057560999961424, "count": 1, "self": 0.0017486259994257125, "children": { "RLTrainer._checkpoint": { "total": 0.10882698400018853, "count": 1, "self": 0.10882698400018853 } } } } } } }