| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.2928386628627777, | |
| "min": 0.2808834910392761, | |
| "max": 1.5365270376205444, | |
| "count": 50 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 5894.2568359375, | |
| "min": 5550.2578125, | |
| "max": 30878.046875, | |
| "count": 50 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 999947.0, | |
| "min": 19968.0, | |
| "max": 999947.0, | |
| "count": 50 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 999947.0, | |
| "min": 19968.0, | |
| "max": 999947.0, | |
| "count": 50 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.6337957978248596, | |
| "min": -0.0891326516866684, | |
| "max": 0.6548319458961487, | |
| "count": 50 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 121.68879699707031, | |
| "min": -14.439489364624023, | |
| "max": 127.27035522460938, | |
| "count": 50 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": -0.007049087900668383, | |
| "min": -0.03438590094447136, | |
| "max": 0.463748961687088, | |
| "count": 50 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": -1.3534249067306519, | |
| "min": -6.395777702331543, | |
| "max": 73.736083984375, | |
| "count": 50 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.06274886612873219, | |
| "min": 0.06274886612873219, | |
| "max": 0.07449785151129816, | |
| "count": 50 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.5647397951585897, | |
| "min": 0.28386088515010977, | |
| "max": 0.7197455395459353, | |
| "count": 50 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.01632938282881952, | |
| "min": 0.0009238557525356134, | |
| "max": 0.017708753124533433, | |
| "count": 50 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.14696444545937568, | |
| "min": 0.00831470177282052, | |
| "max": 0.1664805162262044, | |
| "count": 50 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 2.875399041566666e-06, | |
| "min": 2.875399041566666e-06, | |
| "max": 0.0002969568010144, | |
| "count": 50 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 2.5878591374099994e-05, | |
| "min": 2.5878591374099994e-05, | |
| "max": 0.0025506196497934995, | |
| "count": 50 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.10095843333333335, | |
| "min": 0.10095843333333335, | |
| "max": 0.19898559999999998, | |
| "count": 50 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 0.9086259000000001, | |
| "min": 0.7959423999999999, | |
| "max": 1.8502064999999999, | |
| "count": 50 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.00010574748999999997, | |
| "min": 0.00010574748999999997, | |
| "max": 0.00989866144, | |
| "count": 50 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.0009517274099999997, | |
| "min": 0.0009517274099999997, | |
| "max": 0.08503562934999999, | |
| "count": 50 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.013020750135183334, | |
| "min": 0.012529483996331692, | |
| "max": 0.7789566516876221, | |
| "count": 50 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 0.11718675494194031, | |
| "min": 0.1127653568983078, | |
| "max": 3.1158266067504883, | |
| "count": 50 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 281.61971830985914, | |
| "min": 281.61971830985914, | |
| "max": 999.0, | |
| "count": 50 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 19995.0, | |
| "min": 15629.0, | |
| "max": 29061.0, | |
| "count": 50 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.7183802650428155, | |
| "min": -1.0000000521540642, | |
| "max": 1.7183802650428155, | |
| "count": 50 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 122.0049988180399, | |
| "min": -25.088201582431793, | |
| "max": 122.0049988180399, | |
| "count": 50 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.7183802650428155, | |
| "min": -1.0000000521540642, | |
| "max": 1.7183802650428155, | |
| "count": 50 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 122.0049988180399, | |
| "min": -25.088201582431793, | |
| "max": 122.0049988180399, | |
| "count": 50 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.03746965001615971, | |
| "min": 0.03746965001615971, | |
| "max": 12.048488164320588, | |
| "count": 50 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 2.6603451511473395, | |
| "min": 2.5668109870312037, | |
| "max": 192.7758106291294, | |
| "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": "1680018665", | |
| "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1680020882" | |
| }, | |
| "total": 2216.771151455, | |
| "count": 1, | |
| "self": 0.7891267029995106, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.10739385400029278, | |
| "count": 1, | |
| "self": 0.10739385400029278 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 2215.8746308980003, | |
| "count": 1, | |
| "self": 1.3153144308416813, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 5.9751849700001, | |
| "count": 1, | |
| "self": 5.9751849700001 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 2208.4467628901584, | |
| "count": 64174, | |
| "self": 1.412703235223944, | |
| "children": { | |
| "env_step": { | |
| "total": 1582.0462280959287, | |
| "count": 64174, | |
| "self": 1477.2499674110236, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 104.0307137649529, | |
| "count": 64174, | |
| "self": 4.55181682294824, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 99.47889694200467, | |
| "count": 62563, | |
| "self": 99.47889694200467 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.7655469199521576, | |
| "count": 64174, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 2211.343897246998, | |
| "count": 64174, | |
| "is_parallel": true, | |
| "self": 845.9647931480599, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.0018788109996421554, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006560610004271439, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0012227499992150115, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0012227499992150115 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.04709211899989896, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005314039999575471, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.0005800260000796698, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0005800260000796698 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.04432440899972789, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.04432440899972789 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0016562800001338474, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0003438699995967909, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0013124100005370565, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0013124100005370565 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1365.3791040989381, | |
| "count": 64173, | |
| "is_parallel": true, | |
| "self": 30.698590465921825, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 22.294069002011383, | |
| "count": 64173, | |
| "is_parallel": true, | |
| "self": 22.294069002011383 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1222.142585048945, | |
| "count": 64173, | |
| "is_parallel": true, | |
| "self": 1222.142585048945 | |
| }, | |
| "steps_from_proto": { | |
| "total": 90.24385958205994, | |
| "count": 64173, | |
| "is_parallel": true, | |
| "self": 18.896714161032378, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 71.34714542102756, | |
| "count": 513384, | |
| "is_parallel": true, | |
| "self": 71.34714542102756 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 624.9878315590058, | |
| "count": 64174, | |
| "self": 2.5063146079914986, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 116.4424778490179, | |
| "count": 64174, | |
| "self": 116.18871289801746, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.2537649510004485, | |
| "count": 2, | |
| "self": 0.2537649510004485 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 506.0390391019964, | |
| "count": 458, | |
| "self": 324.4800078670337, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 181.55903123496273, | |
| "count": 22749, | |
| "self": 181.55903123496273 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.5519999578827992e-06, | |
| "count": 1, | |
| "self": 1.5519999578827992e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.13736705500014068, | |
| "count": 1, | |
| "self": 0.0018593439999676775, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.135507711000173, | |
| "count": 1, | |
| "self": 0.135507711000173 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |