| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.6050494909286499, |
| "min": 0.6050494909286499, |
| "max": 0.8366415500640869, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 18093.400390625, |
| "min": 12879.2548828125, |
| "max": 25483.14453125, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 1979883.0, |
| "min": 1019966.0, |
| "max": 1979883.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 1979883.0, |
| "min": 1019966.0, |
| "max": 1979883.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.62385094165802, |
| "min": 0.21211732923984528, |
| "max": 0.6899233460426331, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 177.79751586914062, |
| "min": 34.999359130859375, |
| "max": 194.5907745361328, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.018732663244009018, |
| "min": -0.016395842656493187, |
| "max": 0.02733149379491806, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 5.338809013366699, |
| "min": -2.7053141593933105, |
| "max": 7.570823669433594, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 274.0571428571429, |
| "min": 260.8256880733945, |
| "max": 702.4090909090909, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28776.0, |
| "min": 15453.0, |
| "max": 31444.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.6687866522442727, |
| "min": 0.7518635967915709, |
| "max": 1.716990372739159, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 175.22259848564863, |
| "min": 16.54099912941456, |
| "max": 185.8733986467123, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.6687866522442727, |
| "min": 0.7518635967915709, |
| "max": 1.716990372739159, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 175.22259848564863, |
| "min": 16.54099912941456, |
| "max": 185.8733986467123, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.02576101848667133, |
| "min": 0.023524496236008618, |
| "max": 0.08017137258800423, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 2.7049069411004893, |
| "min": 1.7637701969360933, |
| "max": 3.418516769306734, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06855222881477814, |
| "min": 0.06581879631201712, |
| "max": 0.07266657747234041, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.959731203406894, |
| "min": 0.6165068184463801, |
| "max": 1.0516260387569978, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.014468770938817346, |
| "min": 0.007192014726918317, |
| "max": 0.015923273303390793, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.20256279314344283, |
| "min": 0.06472813254226485, |
| "max": 0.23874681045708715, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 5.1469839986571415e-06, |
| "min": 5.1469839986571415e-06, |
| "max": 0.00014839503386833888, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 7.205777598119998e-05, |
| "min": 7.205777598119998e-05, |
| "max": 0.0020257139747622502, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10171562857142857, |
| "min": 0.10171562857142857, |
| "max": 0.14946499444444444, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4240188, |
| "min": 1.34518495, |
| "max": 2.1564492000000004, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0008676427228571425, |
| "min": 0.0008676427228571425, |
| "max": 0.02473755072277778, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.012146998119999995, |
| "min": 0.012146998119999995, |
| "max": 0.33769135122499994, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.008959934115409851, |
| "min": 0.00835987739264965, |
| "max": 0.01113196648657322, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.12543907761573792, |
| "min": 0.0981353372335434, |
| "max": 0.15584753453731537, |
| "count": 33 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 33 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 33 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1715156388", |
| "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume", |
| "mlagents_version": "1.1.0.dev0", |
| "mlagents_envs_version": "1.1.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.2.1+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1715158946" |
| }, |
| "total": 2558.318411821, |
| "count": 1, |
| "self": 0.4771156560000236, |
| "children": { |
| "run_training.setup": { |
| "total": 0.051621190999867395, |
| "count": 1, |
| "self": 0.051621190999867395 |
| }, |
| "TrainerController.start_learning": { |
| "total": 2557.7896749740003, |
| "count": 1, |
| "self": 1.5009321149082098, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.1861396180001975, |
| "count": 1, |
| "self": 2.1861396180001975 |
| }, |
| "TrainerController.advance": { |
| "total": 2554.007595873092, |
| "count": 64646, |
| "self": 1.5691814611809605, |
| "children": { |
| "env_step": { |
| "total": 1868.7834362149733, |
| "count": 64646, |
| "self": 1727.1443113118885, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 140.72589767201407, |
| "count": 64646, |
| "self": 5.442068254879814, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 135.28382941713426, |
| "count": 62549, |
| "self": 135.28382941713426 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.9132272310707776, |
| "count": 64646, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 2551.910830787956, |
| "count": 64646, |
| "is_parallel": true, |
| "self": 963.0787922048903, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.002196669999648293, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006604640002478845, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0015362059994004085, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0015362059994004085 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05332669800009171, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0007138900009522331, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.000479559999803314, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.000479559999803314 |
| }, |
| "communicator.exchange": { |
| "total": 0.05028351399960229, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.05028351399960229 |
| }, |
| "steps_from_proto": { |
| "total": 0.0018497339997338713, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00036156599890091456, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0014881680008329567, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0014881680008329567 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1588.8320385830657, |
| "count": 64645, |
| "is_parallel": true, |
| "self": 36.778021791972606, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 26.658363137064953, |
| "count": 64645, |
| "is_parallel": true, |
| "self": 26.658363137064953 |
| }, |
| "communicator.exchange": { |
| "total": 1413.5190357680112, |
| "count": 64645, |
| "is_parallel": true, |
| "self": 1413.5190357680112 |
| }, |
| "steps_from_proto": { |
| "total": 111.8766178860169, |
| "count": 64645, |
| "is_parallel": true, |
| "self": 23.183875133140646, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 88.69274275287626, |
| "count": 517160, |
| "is_parallel": true, |
| "self": 88.69274275287626 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 683.6549781969379, |
| "count": 64646, |
| "self": 2.9432743299876165, |
| "children": { |
| "process_trajectory": { |
| "total": 145.74747356994885, |
| "count": 64646, |
| "self": 145.46585365194915, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.28161991799970565, |
| "count": 2, |
| "self": 0.28161991799970565 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 534.9642302970014, |
| "count": 473, |
| "self": 317.0337109129723, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 217.93051938402914, |
| "count": 22764, |
| "self": 217.93051938402914 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.0049998309114017e-06, |
| "count": 1, |
| "self": 1.0049998309114017e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.09500636299981124, |
| "count": 1, |
| "self": 0.002084752999508055, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.09292161000030319, |
| "count": 1, |
| "self": 0.09292161000030319 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
