| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.3918796181678772, |
| "min": 0.3918796181678772, |
| "max": 1.432897925376892, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 11712.498046875, |
| "min": 11712.498046875, |
| "max": 43468.390625, |
| "count": 33 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 989966.0, |
| "min": 29952.0, |
| "max": 989966.0, |
| "count": 33 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 989966.0, |
| "min": 29952.0, |
| "max": 989966.0, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.536288857460022, |
| "min": -0.09727934002876282, |
| "max": 0.5621100664138794, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 146.94314575195312, |
| "min": -23.444320678710938, |
| "max": 159.0771484375, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.02183660864830017, |
| "min": -0.15648655593395233, |
| "max": 0.6677581071853638, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -5.9832305908203125, |
| "min": -42.5643424987793, |
| "max": 158.2586669921875, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06991227315544772, |
| "min": 0.06571033553059567, |
| "max": 0.07291444648577015, |
| "count": 33 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9787718241762682, |
| "min": 0.49656527318882, |
| "max": 1.0509746557994124, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.01449578115335455, |
| "min": 0.0008423677689674443, |
| "max": 0.02560277148010601, |
| "count": 33 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.2029409361469637, |
| "min": 0.010950780996576776, |
| "max": 0.3086068835145138, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 7.304990422178573e-06, |
| "min": 7.304990422178573e-06, |
| "max": 0.00029515063018788575, |
| "count": 33 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.00010226986591050002, |
| "min": 0.00010226986591050002, |
| "max": 0.0036331531889489998, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10243496428571428, |
| "min": 0.10243496428571428, |
| "max": 0.19838354285714285, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4340894999999998, |
| "min": 1.3886848, |
| "max": 2.6110510000000002, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00025325293214285724, |
| "min": 0.00025325293214285724, |
| "max": 0.00983851593142857, |
| "count": 33 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0035455410500000017, |
| "min": 0.0035455410500000017, |
| "max": 0.12112399490000002, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.015974190086126328, |
| "min": 0.015586605295538902, |
| "max": 0.7137619256973267, |
| "count": 33 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.223638653755188, |
| "min": 0.21821247041225433, |
| "max": 4.996333599090576, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 353.5679012345679, |
| "min": 344.33720930232556, |
| "max": 999.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 28639.0, |
| "min": 15984.0, |
| "max": 33300.0, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.5728674793615938, |
| "min": -1.0000000521540642, |
| "max": 1.612021153201075, |
| "count": 33 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 125.8293983489275, |
| "min": -30.76400177180767, |
| "max": 137.0217980220914, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.5728674793615938, |
| "min": -1.0000000521540642, |
| "max": 1.612021153201075, |
| "count": 33 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 125.8293983489275, |
| "min": -30.76400177180767, |
| "max": 137.0217980220914, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.0582021035879734, |
| "min": 0.057874280766940074, |
| "max": 15.165969615802169, |
| "count": 33 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 4.656168287037872, |
| "min": 4.656168287037872, |
| "max": 242.6555138528347, |
| "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": "1779035143", |
| "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", |
| "command_line_arguments": "/home/samuele_albani/mamba/envs/test-mlagents/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --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": "1779036813" |
| }, |
| "total": 1669.185233170003, |
| "count": 1, |
| "self": 0.21999245200277073, |
| "children": { |
| "run_training.setup": { |
| "total": 0.017982979999942472, |
| "count": 1, |
| "self": 0.017982979999942472 |
| }, |
| "TrainerController.start_learning": { |
| "total": 1668.9472577380002, |
| "count": 1, |
| "self": 1.2191208102594828, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 2.7183730639990245, |
| "count": 1, |
| "self": 2.7183730639990245 |
| }, |
| "TrainerController.advance": { |
| "total": 1664.9213565217433, |
| "count": 63805, |
| "self": 0.9556893021144788, |
| "children": { |
| "env_step": { |
| "total": 1059.3000225896285, |
| "count": 63805, |
| "self": 819.2708673889574, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 239.24679599632145, |
| "count": 63805, |
| "self": 3.216797847486305, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 236.02999814883515, |
| "count": 62563, |
| "self": 236.02999814883515 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.7823592043496319, |
| "count": 63805, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 1666.1665487494247, |
| "count": 63805, |
| "is_parallel": true, |
| "self": 912.1419036801744, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.001894439999887254, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0009658909948484506, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0009285490050388034, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0009285490050388034 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.032243505000224104, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00020338200192782097, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00017876999845611863, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00017876999845611863 |
| }, |
| "communicator.exchange": { |
| "total": 0.031183600000076694, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.031183600000076694 |
| }, |
| "steps_from_proto": { |
| "total": 0.0006777529997634701, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00017024599947035313, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.000507507000293117, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.000507507000293117 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 754.0246450692503, |
| "count": 63804, |
| "is_parallel": true, |
| "self": 11.448201521187002, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 7.483290765125275, |
| "count": 63804, |
| "is_parallel": true, |
| "self": 7.483290765125275 |
| }, |
| "communicator.exchange": { |
| "total": 704.9716403083585, |
| "count": 63804, |
| "is_parallel": true, |
| "self": 704.9716403083585 |
| }, |
| "steps_from_proto": { |
| "total": 30.121512474579504, |
| "count": 63804, |
| "is_parallel": true, |
| "self": 7.401650109630282, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 22.719862364949222, |
| "count": 510432, |
| "is_parallel": true, |
| "self": 22.719862364949222 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 604.6656446300003, |
| "count": 63805, |
| "self": 2.14300882968746, |
| "children": { |
| "process_trajectory": { |
| "total": 102.21295523031586, |
| "count": 63805, |
| "self": 101.98544315331674, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.22751207699911902, |
| "count": 2, |
| "self": 0.22751207699911902 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 500.309680569997, |
| "count": 451, |
| "self": 205.30219273233888, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 295.0074878376581, |
| "count": 22815, |
| "self": 295.0074878376581 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 5.459987733047456e-07, |
| "count": 1, |
| "self": 5.459987733047456e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.08840679599961732, |
| "count": 1, |
| "self": 0.0008850309968693182, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.087521765002748, |
| "count": 1, |
| "self": 0.087521765002748 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
