| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 1.070654034614563, |
| "min": 0.9521423578262329, |
| "max": 1.433210849761963, |
| "count": 10 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 31931.185546875, |
| "min": 28518.568359375, |
| "max": 43477.8828125, |
| "count": 10 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 299904.0, |
| "min": 29952.0, |
| "max": 299904.0, |
| "count": 10 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 299904.0, |
| "min": 29952.0, |
| "max": 299904.0, |
| "count": 10 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": -0.06418920308351517, |
| "min": -0.13325481116771698, |
| "max": -0.06418920308351517, |
| "count": 10 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": -15.469598770141602, |
| "min": -31.98115348815918, |
| "max": -15.469598770141602, |
| "count": 10 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.02616559900343418, |
| "min": 0.02616559900343418, |
| "max": 0.3077893853187561, |
| "count": 10 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 6.305909156799316, |
| "min": 6.305909156799316, |
| "max": 73.86945343017578, |
| "count": 10 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.07009747505308819, |
| "min": 0.06695508189111199, |
| "max": 0.07284647788660603, |
| "count": 10 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9813646507432348, |
| "min": 0.5067681622465312, |
| "max": 0.9813646507432348, |
| "count": 10 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.0015841342877873606, |
| "min": 0.000637893092489283, |
| "max": 0.007851968418081775, |
| "count": 10 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.02217788002902305, |
| "min": 0.005741037832403547, |
| "max": 0.05496377892657242, |
| "count": 10 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 0.00027148019522089045, |
| "min": 0.00027148019522089045, |
| "max": 0.00029838354339596195, |
| "count": 10 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 0.0038007227330924664, |
| "min": 0.0020886848037717336, |
| "max": 0.0038007227330924664, |
| "count": 10 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.19049339523809522, |
| "min": 0.19049339523809522, |
| "max": 0.19946118095238097, |
| "count": 10 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 2.666907533333333, |
| "min": 1.3962282666666668, |
| "max": 2.666907533333333, |
| "count": 10 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.009050290184285714, |
| "min": 0.009050290184285714, |
| "max": 0.009946171977142856, |
| "count": 10 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.12670406258, |
| "min": 0.06962320384, |
| "max": 0.12670406258, |
| "count": 10 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.02606460452079773, |
| "min": 0.02606460452079773, |
| "max": 0.4960919916629791, |
| "count": 10 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.3649044632911682, |
| "min": 0.3649044632911682, |
| "max": 3.4726438522338867, |
| "count": 10 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 970.59375, |
| "min": 951.1470588235294, |
| "max": 999.0, |
| "count": 10 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 31059.0, |
| "min": 15984.0, |
| "max": 32705.0, |
| "count": 10 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": -0.7297273187926321, |
| "min": -1.0000000521540642, |
| "max": -0.7018261341297108, |
| "count": 10 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": -24.08100152015686, |
| "min": -31.00000161677599, |
| "max": -16.000000834465027, |
| "count": 10 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": -0.7297273187926321, |
| "min": -1.0000000521540642, |
| "max": -0.7018261341297108, |
| "count": 10 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": -24.08100152015686, |
| "min": -31.00000161677599, |
| "max": -16.000000834465027, |
| "count": 10 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.27368933312369115, |
| "min": 0.27368933312369115, |
| "max": 10.269564557820559, |
| "count": 10 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 9.031747993081808, |
| "min": 6.884992823470384, |
| "max": 164.31303292512894, |
| "count": 10 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 10 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 10 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1756729438", |
| "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [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": "1.2.0.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": "1756730030" |
| }, |
| "total": 592.11048138, |
| "count": 1, |
| "self": 0.28643452300013905, |
| "children": { |
| "run_training.setup": { |
| "total": 0.023989851000010276, |
| "count": 1, |
| "self": 0.023989851000010276 |
| }, |
| "TrainerController.start_learning": { |
| "total": 591.8000570059999, |
| "count": 1, |
| "self": 0.3716992860067876, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.064057324000032, |
| "count": 1, |
| "self": 3.064057324000032 |
| }, |
| "TrainerController.advance": { |
| "total": 588.1607625909933, |
| "count": 19121, |
| "self": 0.38297415896636267, |
| "children": { |
| "env_step": { |
| "total": 392.833443099016, |
| "count": 19121, |
| "self": 349.5664556460398, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 43.03532465398473, |
| "count": 19121, |
| "self": 1.3582888039887848, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 41.677035849995946, |
| "count": 19080, |
| "self": 41.677035849995946 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.23166279899146502, |
| "count": 19120, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 590.4352214169974, |
| "count": 19120, |
| "is_parallel": true, |
| "self": 272.91052435799986, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.004680985999925724, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.003481777000047259, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001199208999878465, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001199208999878465 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.08978201000002173, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005361890000585845, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004836949999571516, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004836949999571516 |
| }, |
| "communicator.exchange": { |
| "total": 0.08709983599999305, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.08709983599999305 |
| }, |
| "steps_from_proto": { |
| "total": 0.0016622900000129448, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00035980199982077465, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013024880001921701, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013024880001921701 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 317.5246970589975, |
| "count": 19119, |
| "is_parallel": true, |
| "self": 9.438681183996664, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 6.9537692859956906, |
| "count": 19119, |
| "is_parallel": true, |
| "self": 6.9537692859956906 |
| }, |
| "communicator.exchange": { |
| "total": 272.11048811701255, |
| "count": 19119, |
| "is_parallel": true, |
| "self": 272.11048811701255 |
| }, |
| "steps_from_proto": { |
| "total": 29.021758471992598, |
| "count": 19119, |
| "is_parallel": true, |
| "self": 5.787319745959849, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 23.23443872603275, |
| "count": 152952, |
| "is_parallel": true, |
| "self": 23.23443872603275 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 194.94434533301092, |
| "count": 19120, |
| "self": 0.5332531730017536, |
| "children": { |
| "process_trajectory": { |
| "total": 34.86885428300832, |
| "count": 19120, |
| "self": 34.86885428300832 |
| }, |
| "_update_policy": { |
| "total": 159.54223787700084, |
| "count": 113, |
| "self": 90.5846736840067, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 68.95756419299414, |
| "count": 7023, |
| "self": 68.95756419299414 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 1.5959999473125208e-06, |
| "count": 1, |
| "self": 1.5959999473125208e-06 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.2035362089998216, |
| "count": 1, |
| "self": 0.0017089819998545863, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.20182722699996702, |
| "count": 1, |
| "self": 0.20182722699996702 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
