| { |
| "name": "root", |
| "gauges": { |
| "Pyramids.Policy.Entropy.mean": { |
| "value": 0.27550312876701355, |
| "min": 0.25834792852401733, |
| "max": 1.4050623178482056, |
| "count": 66 |
| }, |
| "Pyramids.Policy.Entropy.sum": { |
| "value": 8243.0537109375, |
| "min": 7746.3046875, |
| "max": 42623.96875, |
| "count": 66 |
| }, |
| "Pyramids.Step.mean": { |
| "value": 1979900.0, |
| "min": 29952.0, |
| "max": 1979900.0, |
| "count": 66 |
| }, |
| "Pyramids.Step.sum": { |
| "value": 1979900.0, |
| "min": 29952.0, |
| "max": 1979900.0, |
| "count": 66 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 0.6988829374313354, |
| "min": -0.11405694484710693, |
| "max": 0.6988829374313354, |
| "count": 66 |
| }, |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 199.88052368164062, |
| "min": -27.48772430419922, |
| "max": 200.10537719726562, |
| "count": 66 |
| }, |
| "Pyramids.Policy.RndValueEstimate.mean": { |
| "value": 0.01821029745042324, |
| "min": -0.0070686121471226215, |
| "max": 0.6022505164146423, |
| "count": 66 |
| }, |
| "Pyramids.Policy.RndValueEstimate.sum": { |
| "value": 5.2081451416015625, |
| "min": -1.9014567136764526, |
| "max": 142.73336791992188, |
| "count": 66 |
| }, |
| "Pyramids.Losses.PolicyLoss.mean": { |
| "value": 0.06929339248260173, |
| "min": 0.06282748713038884, |
| "max": 0.07449612383996802, |
| "count": 66 |
| }, |
| "Pyramids.Losses.PolicyLoss.sum": { |
| "value": 0.9701074947564243, |
| "min": 0.5001661447938947, |
| "max": 1.0594284480789167, |
| "count": 66 |
| }, |
| "Pyramids.Losses.ValueLoss.mean": { |
| "value": 0.014041961081342638, |
| "min": 9.133431192385169e-05, |
| "max": 0.017774556835112667, |
| "count": 66 |
| }, |
| "Pyramids.Losses.ValueLoss.sum": { |
| "value": 0.19658745513879694, |
| "min": 0.001187346055010072, |
| "max": 0.21795929489114008, |
| "count": 66 |
| }, |
| "Pyramids.Policy.LearningRate.mean": { |
| "value": 5.335469650114285e-06, |
| "min": 5.335469650114285e-06, |
| "max": 0.0002975753150939428, |
| "count": 66 |
| }, |
| "Pyramids.Policy.LearningRate.sum": { |
| "value": 7.469657510159999e-05, |
| "min": 7.469657510159999e-05, |
| "max": 0.0037911269862910494, |
| "count": 66 |
| }, |
| "Pyramids.Policy.Epsilon.mean": { |
| "value": 0.10177845714285716, |
| "min": 0.10177845714285716, |
| "max": 0.19919177142857142, |
| "count": 66 |
| }, |
| "Pyramids.Policy.Epsilon.sum": { |
| "value": 1.4248984000000002, |
| "min": 1.3943424, |
| "max": 2.66370895, |
| "count": 66 |
| }, |
| "Pyramids.Policy.Beta.mean": { |
| "value": 0.00018766786857142857, |
| "min": 0.00018766786857142857, |
| "max": 0.009919257965714285, |
| "count": 66 |
| }, |
| "Pyramids.Policy.Beta.sum": { |
| "value": 0.00262735016, |
| "min": 0.00262735016, |
| "max": 0.12638452410499998, |
| "count": 66 |
| }, |
| "Pyramids.Losses.RNDLoss.mean": { |
| "value": 0.010234856978058815, |
| "min": 0.009864476509392262, |
| "max": 0.745283305644989, |
| "count": 66 |
| }, |
| "Pyramids.Losses.RNDLoss.sum": { |
| "value": 0.1432880014181137, |
| "min": 0.1381026655435562, |
| "max": 5.216983318328857, |
| "count": 66 |
| }, |
| "Pyramids.Environment.EpisodeLength.mean": { |
| "value": 275.64220183486236, |
| "min": 268.60550458715596, |
| "max": 999.0, |
| "count": 66 |
| }, |
| "Pyramids.Environment.EpisodeLength.sum": { |
| "value": 30045.0, |
| "min": 15984.0, |
| "max": 34141.0, |
| "count": 66 |
| }, |
| "Pyramids.Environment.CumulativeReward.mean": { |
| "value": 1.6892908945679665, |
| "min": -1.0000000521540642, |
| "max": 1.7180094158030905, |
| "count": 66 |
| }, |
| "Pyramids.Environment.CumulativeReward.sum": { |
| "value": 185.8219984024763, |
| "min": -31.99480167031288, |
| "max": 185.8219984024763, |
| "count": 66 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.mean": { |
| "value": 1.6892908945679665, |
| "min": -1.0000000521540642, |
| "max": 1.7180094158030905, |
| "count": 66 |
| }, |
| "Pyramids.Policy.ExtrinsicReward.sum": { |
| "value": 185.8219984024763, |
| "min": -31.99480167031288, |
| "max": 185.8219984024763, |
| "count": 66 |
| }, |
| "Pyramids.Policy.RndReward.mean": { |
| "value": 0.029029120984540153, |
| "min": 0.0283566456418399, |
| "max": 15.885404660366476, |
| "count": 66 |
| }, |
| "Pyramids.Policy.RndReward.sum": { |
| "value": 3.1932033082994167, |
| "min": 3.0069052900362294, |
| "max": 254.1664745658636, |
| "count": 66 |
| }, |
| "Pyramids.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 66 |
| }, |
| "Pyramids.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 66 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1742279590", |
| "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", |
| "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": "2.6.0+cu124", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1742284517" |
| }, |
| "total": 4926.48045705, |
| "count": 1, |
| "self": 0.5444621679998818, |
| "children": { |
| "run_training.setup": { |
| "total": 0.024440325000000485, |
| "count": 1, |
| "self": 0.024440325000000485 |
| }, |
| "TrainerController.start_learning": { |
| "total": 4925.911554557, |
| "count": 1, |
| "self": 2.9366226261490738, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.5656723109999575, |
| "count": 1, |
| "self": 3.5656723109999575 |
| }, |
| "TrainerController.advance": { |
| "total": 4919.3157502618515, |
| "count": 128070, |
| "self": 3.003288209868515, |
| "children": { |
| "env_step": { |
| "total": 3445.7855705750335, |
| "count": 128070, |
| "self": 3119.412128281993, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 324.68119087800596, |
| "count": 128070, |
| "self": 9.874450978089044, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 314.8067398999169, |
| "count": 125065, |
| "self": 314.8067398999169 |
| } |
| } |
| }, |
| "workers": { |
| "total": 1.6922514150347752, |
| "count": 128070, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 4915.762005272174, |
| "count": 128070, |
| "is_parallel": true, |
| "self": 2033.5907745992172, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0060559099999863975, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.004594974999804435, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.001460935000181962, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.001460935000181962 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.05045673799997985, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0005193279999957667, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.00047720299994580273, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00047720299994580273 |
| }, |
| "communicator.exchange": { |
| "total": 0.04776102899995749, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.04776102899995749 |
| }, |
| "steps_from_proto": { |
| "total": 0.0016991780000807921, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00036389200033681846, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.0013352859997439737, |
| "count": 8, |
| "is_parallel": true, |
| "self": 0.0013352859997439737 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 2882.171230672957, |
| "count": 128069, |
| "is_parallel": true, |
| "self": 68.64760795904567, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 47.6284434188525, |
| "count": 128069, |
| "is_parallel": true, |
| "self": 47.6284434188525 |
| }, |
| "communicator.exchange": { |
| "total": 2563.0016967229303, |
| "count": 128069, |
| "is_parallel": true, |
| "self": 2563.0016967229303 |
| }, |
| "steps_from_proto": { |
| "total": 202.8934825721284, |
| "count": 128069, |
| "is_parallel": true, |
| "self": 41.42429864008659, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 161.4691839320418, |
| "count": 1024552, |
| "is_parallel": true, |
| "self": 161.4691839320418 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_advance": { |
| "total": 1470.5268914769495, |
| "count": 128070, |
| "self": 5.889992732891869, |
| "children": { |
| "process_trajectory": { |
| "total": 270.16659548205894, |
| "count": 128070, |
| "self": 269.7044371840591, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.4621582979998493, |
| "count": 4, |
| "self": 0.4621582979998493 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 1194.4703032619987, |
| "count": 921, |
| "self": 655.8847790780462, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 538.5855241839524, |
| "count": 45588, |
| "self": 538.5855241839524 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 9.750001481734216e-07, |
| "count": 1, |
| "self": 9.750001481734216e-07 |
| }, |
| "TrainerController._save_models": { |
| "total": 0.09350838299997122, |
| "count": 1, |
| "self": 0.0018763500002023648, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.09163203299976885, |
| "count": 1, |
| "self": 0.09163203299976885 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
