{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.24800357222557068, "min": 0.2137782722711563, "max": 1.4664843082427979, "count": 66 }, "Pyramids.Policy.Entropy.sum": { "value": 7416.298828125, "min": 6454.3935546875, "max": 44487.26953125, "count": 66 }, "Pyramids.Step.mean": { "value": 1979960.0, "min": 29952.0, "max": 1979960.0, "count": 66 }, "Pyramids.Step.sum": { "value": 1979960.0, "min": 29952.0, "max": 1979960.0, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7750120162963867, "min": -0.09869357943534851, "max": 0.8393959999084473, "count": 66 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 227.07852172851562, "min": -23.587764739990234, "max": 255.00885009765625, "count": 66 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.0029208590276539326, "min": -0.028419921174645424, "max": 0.40528467297554016, "count": 66 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 0.8558117151260376, "min": -7.957577705383301, "max": 96.0524673461914, "count": 66 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07155785263780634, "min": 0.06401901965817706, "max": 0.07438902306105975, "count": 66 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0018099369292888, "min": 0.5083555090211027, "max": 1.0637672329253025, "count": 66 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.013265262272902529, "min": 0.00010484618660803808, "max": 0.017355979519336307, "count": 66 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.1857136718206354, "min": 0.0013630004259044951, "max": 0.25093374454302775, "count": 66 }, "Pyramids.Policy.LearningRate.mean": { "value": 5.28389109587857e-06, "min": 5.28389109587857e-06, "max": 0.0002975753150939428, "count": 66 }, "Pyramids.Policy.LearningRate.sum": { "value": 7.397447534229998e-05, "min": 7.397447534229998e-05, "max": 0.00363756683747775, "count": 66 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10176126428571429, "min": 0.10176126428571429, "max": 0.19919177142857142, "count": 66 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4246577, "min": 1.3845568000000001, "max": 2.6001557000000006, "count": 66 }, "Pyramids.Policy.Beta.mean": { "value": 0.00018595030214285714, "min": 0.00018595030214285714, "max": 0.009919257965714285, "count": 66 }, "Pyramids.Policy.Beta.sum": { "value": 0.00260330423, "min": 0.00260330423, "max": 0.12126097277500002, "count": 66 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.007138731889426708, "min": 0.0066531808115541935, "max": 0.4042229652404785, "count": 66 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.09994224458932877, "min": 0.09314452856779099, "max": 2.8295607566833496, "count": 66 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 236.575, "min": 216.13669064748203, "max": 999.0, "count": 66 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28389.0, "min": 15984.0, "max": 32945.0, "count": 66 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7478561864411535, "min": -1.0000000521540642, "max": 1.772834574705676, "count": 66 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 211.49059855937958, "min": -32.000001668930054, "max": 245.95659844577312, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7478561864411535, "min": -1.0000000521540642, "max": 1.772834574705676, "count": 66 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 211.49059855937958, "min": -32.000001668930054, "max": 245.95659844577312, "count": 66 }, "Pyramids.Policy.RndReward.mean": { "value": 0.017675159525868005, "min": 0.016706443338698036, "max": 9.123851827345788, "count": 66 }, "Pyramids.Policy.RndReward.sum": { "value": 2.1386943026300287, "min": 2.062561700882725, "max": 145.98162923753262, "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": "1707067574", "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 3 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1707072245" }, "total": 4671.053423575, "count": 1, "self": 0.42601222099983715, "children": { "run_training.setup": { "total": 0.045467555999493925, "count": 1, "self": 0.045467555999493925 }, "TrainerController.start_learning": { "total": 4670.581943798001, "count": 1, "self": 2.7136775419048718, "children": { "TrainerController._reset_env": { "total": 2.26388002099975, "count": 1, "self": 2.26388002099975 }, "TrainerController.advance": { "total": 4665.5103417900955, "count": 129516, "self": 3.0415786475441564, "children": { "env_step": { "total": 3423.667683731792, "count": 129516, "self": 3159.7675410407937, "children": { "SubprocessEnvManager._take_step": { "total": 262.16158983772493, "count": 129516, "self": 9.592200320927986, "children": { "TorchPolicy.evaluate": { "total": 252.56938951679695, "count": 125067, "self": 252.56938951679695 } } }, "workers": { "total": 1.7385528532731769, "count": 129516, "self": 0.0, "children": { "worker_root": { "total": 4659.887258529914, "count": 129516, "is_parallel": true, "self": 1737.8123599386809, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0020462779993977165, "count": 1, "is_parallel": true, "self": 0.000630208000075072, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014160699993226444, "count": 8, "is_parallel": true, "self": 0.0014160699993226444 } } }, "UnityEnvironment.step": { "total": 0.05177360400011821, "count": 1, "is_parallel": true, "self": 0.0006036209988451446, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005070510005680262, "count": 1, "is_parallel": true, "self": 0.0005070510005680262 }, "communicator.exchange": { "total": 0.04902255900015007, "count": 1, "is_parallel": true, "self": 0.04902255900015007 }, "steps_from_proto": { "total": 0.0016403730005549733, "count": 1, "is_parallel": true, "self": 0.00032830899999680696, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013120640005581663, "count": 8, "is_parallel": true, "self": 0.0013120640005581663 } } } } } } }, "UnityEnvironment.step": { "total": 2922.0748985912333, "count": 129515, "is_parallel": true, "self": 70.0589943893192, "children": { "UnityEnvironment._generate_step_input": { "total": 51.7430342850148, "count": 129515, "is_parallel": true, "self": 51.7430342850148 }, "communicator.exchange": { "total": 2595.7864470538952, "count": 129515, "is_parallel": true, "self": 2595.7864470538952 }, "steps_from_proto": { "total": 204.486422863004, "count": 129515, "is_parallel": true, "self": 41.12764777292796, "children": { "_process_rank_one_or_two_observation": { "total": 163.35877509007605, "count": 1036120, "is_parallel": true, "self": 163.35877509007605 } } } } } } } } } } }, "trainer_advance": { "total": 1238.8010794107595, "count": 129516, "self": 5.311919556172143, "children": { "process_trajectory": { "total": 256.67963393858463, "count": 129516, "self": 256.2886781425832, "children": { "RLTrainer._checkpoint": { "total": 0.3909557960014354, "count": 4, "self": 0.3909557960014354 } } }, "_update_policy": { "total": 976.8095259160027, "count": 915, "self": 569.3073360291091, "children": { "TorchPPOOptimizer.update": { "total": 407.5021898868936, "count": 45636, "self": 407.5021898868936 } } } } } } }, "trainer_threads": { "total": 1.229000190505758e-06, "count": 1, "self": 1.229000190505758e-06 }, "TrainerController._save_models": { "total": 0.09404321600050025, "count": 1, "self": 0.0014257790007832227, "children": { "RLTrainer._checkpoint": { "total": 0.09261743699971703, "count": 1, "self": 0.09261743699971703 } } } } } } }