| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.5530761480331421, |
| "min": 0.5530761480331421, |
| "max": 1.4809691905975342, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 16415.30078125, |
| "min": 16415.30078125, |
| "max": 44926.6796875, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989887.0, |
| "min": 29952.0, |
| "max": 989887.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989887.0, |
| "min": 29952.0, |
| "max": 989887.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.15354564785957336, |
| "min": -0.13005642592906952, |
| "max": 0.25876039266586304, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 38.693504333496094, |
| "min": -31.47365379333496, |
| "max": 66.50141906738281, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.011929752305150032, |
| "min": 0.011064324527978897, |
| "max": 0.36932405829429626, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 3.0062975883483887, |
| "min": 2.6665022373199463, |
| "max": 87.52980041503906, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.0665086768051927, |
| "min": 0.06561120882349268, |
| "max": 0.07225323932636522, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9311214752726978, |
| "min": 0.4861489415955569, |
| "max": 1.0674934432559071, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.0066596000252421034, |
| "min": 0.0001308562730506333, |
| "max": 0.010215501747769027, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.09323440035338945, |
| "min": 0.0015702752766075993, |
| "max": 0.14301702446876638, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.329633271107141e-06, |
| "min": 7.329633271107141e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010261486579549998, |
| "min": 0.00010261486579549998, |
| "max": 0.0029528101157300004, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10244317857142857, |
| "min": 0.10244317857142857, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4342044999999999, |
| "min": 1.3691136000000002, |
| "max": 2.2755249, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.0002540735392857143, |
| "min": 0.0002540735392857143, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0035570295499999997, |
| "min": 0.0035570295499999997, |
| "max": 0.098438573, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.010774964466691017, |
| "min": 0.010774964466691017, |
| "max": 0.36566081643104553, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.15084950625896454, |
| "min": 0.15084950625896454, |
| "max": 2.5596256256103516, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 622.6304347826087, |
| "min": 579.4423076923077, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28641.0, |
| "min": 15984.0, |
| "max": 33174.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 0.6815564915861773, |
| "min": -1.0000000521540642, |
| "max": 1.0358153531471124, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 31.351598612964153, |
| "min": -32.000001668930054, |
| "max": 55.76919827610254, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 0.6815564915861773, |
| "min": -1.0000000521540642, |
| "max": 1.0358153531471124, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 31.351598612964153, |
| "min": -32.000001668930054, |
| "max": 55.76919827610254, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.07090261457842248, |
| "min": 0.06480223197789971, |
| "max": 6.994913578033447, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.261520270607434, |
| "min": 3.261520270607434, |
| "max": 111.91861724853516, |
| "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": "1688921011", |
| "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 Training2 --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": "1688924484" |
| }, |
| "total": 3473.310910102, |
| "count": 1, |
| "self": 0.6896852370005035, |
| "children": { |
| "run_training.setup": { |
| "total": 0.08105279299979884, |
| "count": 1, |
| "self": 0.08105279299979884 |
| }, |
| "TrainerController.start_learning": { |
| "total": 3472.5401720719997, |
| "count": 1, |
| "self": 2.5933467659579037, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 1.4455693900004007, |
| "count": 1, |
| "self": 1.4455693900004007 |
| }, |
| "TrainerController.advance": { |
| "total": 3468.387072505042, |
| "count": 63201, |
| "self": 2.727794847099176, |
| "children": { |
| "env_step": { |
| "total": 2173.9636474109843, |
| "count": 63201, |
| "self": 2013.5933640200724, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 158.7315983929061, |
| "count": 63201, |
| "self": 7.850027837912876, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 150.88157055499323, |
| "count": 62559, |
| "self": 150.88157055499323 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.6386849980058287, |
| "count": 63201, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 3465.2188885200044, |
| "count": 63201, |
| "is_parallel": true, |
| "self": 1645.3619896879254, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.005535292999866215, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.001752301000578882, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.003782991999287333, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.003782991999287333 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.06728723400010495, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006418510006369615, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00041700299971125787, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00041700299971125787 |
| }, |
| "communicator.exchange": { |
| "total": 0.06380958399995507, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.06380958399995507 |
| }, |
| "steps_from_proto": { |
| "total": 0.0024187959998016595, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00046023399954719935, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.00195856200025446, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.00195856200025446 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 1819.856898832079, |
| "count": 63200, |
| "is_parallel": true, |
| "self": 48.68366635505981, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 27.56247422398974, |
| "count": 63200, |
| "is_parallel": true, |
| "self": 27.56247422398974 |
| }, |
| "communicator.exchange": { |
| "total": 1594.023561070017, |
| "count": 63200, |
| "is_parallel": true, |
| "self": 1594.023561070017 |
| }, |
| "steps_from_proto": { |
| "total": 149.58719718301245, |
| "count": 63200, |
| "is_parallel": true, |
| "self": 31.026908455770354, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 118.5602887272421, |
| "count": 505600, |
| "is_parallel": true, |
| "self": 118.5602887272421 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1291.6956302469584, |
| "count": 63201, |
| "self": 4.94466677295668, |
| "children": { |
| "process_trajectory": { |
| "total": 164.2622141240049, |
| "count": 63201, |
| "self": 164.00998956700505, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.2522245569998631, |
| "count": 2, |
| "self": 0.2522245569998631 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1122.4887493499969, |
| "count": 430, |
| "self": 465.41795774705497, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 657.0707916029419, |
| "count": 22902, |
| "self": 657.0707916029419 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.1549991540960036e-06, |
| "count": 1, |
| "self": 1.1549991540960036e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.11418225600027654, |
| "count": 1, |
| "self": 0.0018844980004359968, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.11229775799984054, |
| "count": 1, |
| "self": 0.11229775799984054 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
