{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.2805362641811371, "min": 0.26187101006507874, "max": 1.4038902521133423, "count": 50 }, "Pyramids.Policy.Entropy.sum": { "value": 8447.5078125, "min": 7818.4208984375, "max": 42588.4140625, "count": 50 }, "Pyramids.Step.mean": { "value": 1499982.0, "min": 29952.0, "max": 1499982.0, "count": 50 }, "Pyramids.Step.sum": { "value": 1499982.0, "min": 29952.0, "max": 1499982.0, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7360298037528992, "min": -0.1420941948890686, "max": 0.7360298037528992, "count": 50 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 216.39276123046875, "min": -33.67632293701172, "max": 216.39276123046875, "count": 50 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.019416235387325287, "min": -0.0005991759244352579, "max": 0.2926444113254547, "count": 50 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 5.708373069763184, "min": -0.17016595602035522, "max": 70.8199462890625, "count": 50 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06701628360975566, "min": 0.06518027532549969, "max": 0.0723619756557541, "count": 50 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9382279705365791, "min": 0.48388459767320663, "max": 1.0628745117768024, "count": 50 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01643277161643959, "min": 7.034291951263579e-05, "max": 0.01807910450692621, "count": 50 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23005880263015427, "min": 0.000984800873176901, "max": 0.26300449160044087, "count": 50 }, "Pyramids.Policy.LearningRate.mean": { "value": 3.119041817495239e-06, "min": 3.119041817495239e-06, "max": 0.00029676708679192377, "count": 50 }, "Pyramids.Policy.LearningRate.sum": { "value": 4.366658544493335e-05, "min": 4.366658544493335e-05, "max": 0.0037056410647863325, "count": 50 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10103964761904763, "min": 0.10103964761904763, "max": 0.19892236190476195, "count": 50 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4145550666666669, "min": 1.3924565333333336, "max": 2.6183896000000004, "count": 50 }, "Pyramids.Policy.Beta.mean": { "value": 0.00011386079714285717, "min": 0.00011386079714285717, "max": 0.009892343954285714, "count": 50 }, "Pyramids.Policy.Beta.sum": { "value": 0.0015940511600000004, "min": 0.0015940511600000004, "max": 0.12352784530000001, "count": 50 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.009632025845348835, "min": 0.009324006736278534, "max": 0.4258716106414795, "count": 50 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.13484835624694824, "min": 0.13053609430789948, "max": 2.9811012744903564, "count": 50 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 254.98290598290598, "min": 254.98290598290598, "max": 999.0, "count": 50 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29833.0, "min": 15984.0, "max": 33146.0, "count": 50 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7447203238636761, "min": -1.0000000521540642, "max": 1.7450172292261288, "count": 50 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 205.87699821591377, "min": -31.995201662182808, "max": 205.87699821591377, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7447203238636761, "min": -1.0000000521540642, "max": 1.7450172292261288, "count": 50 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 205.87699821591377, "min": -31.995201662182808, "max": 205.87699821591377, "count": 50 }, "Pyramids.Policy.RndReward.mean": { "value": 0.02527905977429759, "min": 0.02527905977429759, "max": 8.025034805759788, "count": 50 }, "Pyramids.Policy.RndReward.sum": { "value": 2.9829290533671156, "min": 2.7839028168527875, "max": 128.4005568921566, "count": 50 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1685690465", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training Round 2 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1685693874" }, "total": 3408.8870961410003, "count": 1, "self": 0.8392324600004031, "children": { "run_training.setup": { "total": 0.05715897899972333, "count": 1, "self": 0.05715897899972333 }, "TrainerController.start_learning": { "total": 3407.990704702, "count": 1, "self": 2.0222299819979526, "children": { "TrainerController._reset_env": { "total": 5.032987745000355, "count": 1, "self": 5.032987745000355 }, "TrainerController.advance": { "total": 3400.7905077450027, "count": 96362, "self": 2.1542856119858698, "children": { "env_step": { "total": 2474.100345452152, "count": 96362, "self": 2315.251024856737, "children": { "SubprocessEnvManager._take_step": { "total": 157.65655945813478, "count": 96362, "self": 7.0401761261282445, "children": { "TorchPolicy.evaluate": { "total": 150.61638333200654, "count": 93798, "self": 150.61638333200654 } } }, "workers": { "total": 1.1927611372802858, "count": 96362, "self": 0.0, "children": { "worker_root": { "total": 3400.125349743801, "count": 96362, "is_parallel": true, "self": 1252.4898024297513, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002444652000122005, "count": 1, "is_parallel": true, "self": 0.0006989799999246316, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017456720001973736, "count": 8, "is_parallel": true, "self": 0.0017456720001973736 } } }, "UnityEnvironment.step": { "total": 0.04941046800013282, "count": 1, "is_parallel": true, "self": 0.0005292400001053466, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005273059996397933, "count": 1, "is_parallel": true, "self": 0.0005273059996397933 }, "communicator.exchange": { "total": 0.04649666800014529, "count": 1, "is_parallel": true, "self": 0.04649666800014529 }, "steps_from_proto": { "total": 0.001857254000242392, "count": 1, "is_parallel": true, "self": 0.0003889500003424473, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014683039998999448, "count": 8, "is_parallel": true, "self": 0.0014683039998999448 } } } } } } }, "UnityEnvironment.step": { "total": 2147.6355473140497, "count": 96361, "is_parallel": true, "self": 47.051747808906384, "children": { "UnityEnvironment._generate_step_input": { "total": 33.759662526123975, "count": 96361, "is_parallel": true, "self": 33.759662526123975 }, "communicator.exchange": { "total": 1917.3429039460802, "count": 96361, "is_parallel": true, "self": 1917.3429039460802 }, "steps_from_proto": { "total": 149.48123303293914, "count": 96361, "is_parallel": true, "self": 29.823839682687776, "children": { "_process_rank_one_or_two_observation": { "total": 119.65739335025137, "count": 770888, "is_parallel": true, "self": 119.65739335025137 } } } } } } } } } } }, "trainer_advance": { "total": 924.5358766808649, "count": 96362, "self": 3.8378270508910646, "children": { "process_trajectory": { "total": 157.41070501795411, "count": 96362, "self": 156.96105635895447, "children": { "RLTrainer._checkpoint": { "total": 0.44964865899964934, "count": 3, "self": 0.44964865899964934 } } }, "_update_policy": { "total": 763.2873446120198, "count": 686, "self": 492.1877531830046, "children": { "TorchPPOOptimizer.update": { "total": 271.09959142901516, "count": 34209, "self": 271.09959142901516 } } } } } } }, "trainer_threads": { "total": 1.3729995771427639e-06, "count": 1, "self": 1.3729995771427639e-06 }, "TrainerController._save_models": { "total": 0.14497785699950327, "count": 1, "self": 0.0019984909995400812, "children": { "RLTrainer._checkpoint": { "total": 0.1429793659999632, "count": 1, "self": 0.1429793659999632 } } } } } } }