| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.174331933259964, |
| "min": 0.1634155511856079, |
| "max": 1.3539011478424072, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 5199.275390625, |
| "min": 4920.76904296875, |
| "max": 41071.9453125, |
| "count": 100 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 2999990.0, |
| "min": 29971.0, |
| "max": 2999990.0, |
| "count": 100 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 2999990.0, |
| "min": 29971.0, |
| "max": 2999990.0, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.8177089691162109, |
| "min": -0.12162146717309952, |
| "max": 0.8177089691162109, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 244.49497985839844, |
| "min": -29.189151763916016, |
| "max": 244.49497985839844, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": -0.016530105844140053, |
| "min": -0.016530105844140053, |
| "max": 0.4179201126098633, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": -4.942501544952393, |
| "min": -4.942501544952393, |
| "max": 99.4649887084961, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06848199179186357, |
| "min": 0.06466212648332917, |
| "max": 0.07502674287435676, |
| "count": 100 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9587478850860899, |
| "min": 0.5015066923547186, |
| "max": 1.0873433186823285, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.015651089425144277, |
| "min": 0.00015804969753155585, |
| "max": 0.016540649635966735, |
| "count": 100 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.21911525195201986, |
| "min": 0.0022126957654417818, |
| "max": 0.2315690949035343, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 1.5327066319880936e-06, |
| "min": 1.5327066319880936e-06, |
| "max": 0.00029841252910058573, |
| "count": 100 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 2.145789284783331e-05, |
| "min": 2.145789284783331e-05, |
| "max": 0.003926645091118334, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10051086904761905, |
| "min": 0.10051086904761905, |
| "max": 0.19947084285714287, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4071521666666666, |
| "min": 1.3962959000000001, |
| "max": 2.722487466666667, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 6.103581785714281e-05, |
| "min": 6.103581785714281e-05, |
| "max": 0.009947137201428572, |
| "count": 100 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.0008545014499999993, |
| "min": 0.0008545014499999993, |
| "max": 0.1308972785, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.006058081518858671, |
| "min": 0.005674856714904308, |
| "max": 0.4520358443260193, |
| "count": 100 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.08481314033269882, |
| "min": 0.07944799214601517, |
| "max": 3.1642508506774902, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 226.9770992366412, |
| "min": 220.47407407407408, |
| "max": 999.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 29734.0, |
| "min": 16514.0, |
| "max": 32659.0, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.7730228908871877, |
| "min": -0.9996129529130074, |
| "max": 1.7730228908871877, |
| "count": 100 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 232.26599870622158, |
| "min": -30.98800154030323, |
| "max": 238.23559841513634, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.7730228908871877, |
| "min": -0.9996129529130074, |
| "max": 1.7730228908871877, |
| "count": 100 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 232.26599870622158, |
| "min": -30.98800154030323, |
| "max": 238.23559841513634, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.014302243226881402, |
| "min": 0.014132574172604277, |
| "max": 8.84358102302341, |
| "count": 100 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 1.8735938627214637, |
| "min": 1.6636139633774292, |
| "max": 150.34087739139795, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 100 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1716905491", |
| "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", |
| "mlagents_version": "1.1.0.dev0", |
| "mlagents_envs_version": "1.1.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.3.0+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1716912618" |
| }, |
| "total": 7126.9257419430005, |
| "count": 1, |
| "self": 0.5912733540008048, |
| "children": { |
| "run_training.setup": { |
| "total": 0.055191910000019107, |
| "count": 1, |
| "self": 0.055191910000019107 |
| }, |
| "TrainerController.start_learning": { |
| "total": 7126.279276679, |
| "count": 1, |
| "self": 4.232694962019195, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.251902802000018, |
| "count": 1, |
| "self": 3.251902802000018 |
| }, |
| "TrainerController.advance": { |
| "total": 7118.7049352619815, |
| "count": 194281, |
| "self": 4.380925460969593, |
| "children": { |
| "env_step": { |
| "total": 5204.152235085978, |
| "count": 194281, |
| "self": 4804.859066452045, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 396.66494664101475, |
| "count": 194281, |
| "self": 14.370538872916484, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 382.29440776809827, |
| "count": 187538, |
| "self": 382.29440776809827 |
| } |
| } |
| }, |
| "workers": { |
| "total": 2.6282219929175312, |
| "count": 194281, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 7111.250533665255, |
| "count": 194281, |
| "is_parallel": true, |
| "self": 2683.0334680082115, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0048692880000089644, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0033343620000323426, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0015349259999766218, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0015349259999766218 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.09241287899999406, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0006527569999548177, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004346709999936138, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004346709999936138 |
| }, |
| "communicator.exchange": { |
| "total": 0.08968868200003044, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.08968868200003044 |
| }, |
| "steps_from_proto": { |
| "total": 0.0016367690000151924, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00034669600000825085, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0012900730000069416, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0012900730000069416 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 4428.217065657043, |
| "count": 194280, |
| "is_parallel": true, |
| "self": 102.96457074949649, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 72.11979322382564, |
| "count": 194280, |
| "is_parallel": true, |
| "self": 72.11979322382564 |
| }, |
| "communicator.exchange": { |
| "total": 3948.3265536386925, |
| "count": 194280, |
| "is_parallel": true, |
| "self": 3948.3265536386925 |
| }, |
| "steps_from_proto": { |
| "total": 304.80614804502903, |
| "count": 194280, |
| "is_parallel": true, |
| "self": 62.546481669169566, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 242.25966637585947, |
| "count": 1554240, |
| "is_parallel": true, |
| "self": 242.25966637585947 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1910.1717747150337, |
| "count": 194281, |
| "self": 8.34827071280938, |
| "children": { |
| "process_trajectory": { |
| "total": 404.06855110422947, |
| "count": 194281, |
| "self": 403.36172708823045, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.7068240159990182, |
| "count": 6, |
| "self": 0.7068240159990182 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1497.7549528979948, |
| "count": 1398, |
| "self": 891.7018748839354, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 606.0530780140595, |
| "count": 68328, |
| "self": 606.0530780140595 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.0869998732232489e-06, |
| "count": 1, |
| "self": 1.0869998732232489e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.08974256599958608, |
| "count": 1, |
| "self": 0.0014744359996257117, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.08826812999996037, |
| "count": 1, |
| "self": 0.08826812999996037 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
