{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.18546807765960693, "min": 0.17633308470249176, "max": 1.3745640516281128, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 5572.94482421875, "min": 5301.2421875, "max": 41698.7734375, "count": 100 }, "Pyramids.Step.mean": { "value": 2999999.0, "min": 29952.0, "max": 2999999.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999999.0, "min": 29952.0, "max": 2999999.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.7917275428771973, "min": -0.10109587013721466, "max": 0.909292995929718, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 234.35134887695312, "min": -24.364105224609375, "max": 285.51800537109375, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.03333019092679024, "min": -0.012595859356224537, "max": 0.3700123131275177, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 9.865736961364746, "min": -3.8039495944976807, "max": 87.69291687011719, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07298967267464226, "min": 0.06367239993996916, "max": 0.07409800813172876, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.0218554174449916, "min": 0.501297429334118, "max": 1.0940298073058812, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015727059346058274, "min": 8.814388570693767e-05, "max": 0.016361983265622267, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22017883084481585, "min": 0.0011458705141901898, "max": 0.23490348882464165, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.461970941280956e-06, "min": 1.461970941280956e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.0467593177933383e-05, "min": 2.0467593177933383e-05, "max": 0.003847268717577166, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10048729047619051, "min": 0.10048729047619051, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.406822066666667, "min": 1.3962282666666668, "max": 2.782422833333334, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 5.868031857142869e-05, "min": 5.868031857142869e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008215244600000016, "min": 0.0008215244600000016, "max": 0.12826404105, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008527441881597042, "min": 0.00811397098004818, "max": 0.572655975818634, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.11938418447971344, "min": 0.11359558999538422, "max": 4.008591651916504, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 235.06521739130434, "min": 196.13698630136986, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 32439.0, "min": 15984.0, "max": 33761.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7494802769735782, "min": -1.0000000521540642, "max": 1.8024532217130387, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 239.6787979453802, "min": -31.994001656770706, "max": 273.8567990064621, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7494802769735782, "min": -1.0000000521540642, "max": 1.8024532217130387, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 239.6787979453802, "min": -31.994001656770706, "max": 273.8567990064621, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.020860109220018415, "min": 0.017034575891320607, "max": 10.650940678082407, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.8578349631425226, "min": 2.4213780725258403, "max": 170.4150508493185, "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": "1792870571", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1792876203" }, "total": 5632.233361521001, "count": 1, "self": 0.37255748500138, "children": { "run_training.setup": { "total": 0.026740447000065615, "count": 1, "self": 0.026740447000065615 }, "TrainerController.start_learning": { "total": 5631.834063589, "count": 1, "self": 5.1322612921158, "children": { "TrainerController._reset_env": { "total": 2.172322763000011, "count": 1, "self": 2.172322763000011 }, "TrainerController.advance": { "total": 5624.445110714884, "count": 195781, "self": 4.9454568591945645, "children": { "env_step": { "total": 3729.7946948898275, "count": 195781, "self": 3221.2874682316915, "children": { "SubprocessEnvManager._take_step": { "total": 505.4302440620586, "count": 195781, "self": 15.177331032144593, "children": { "TorchPolicy.evaluate": { "total": 490.252913029914, "count": 187572, "self": 490.252913029914 } } }, "workers": { "total": 3.076982596077414, "count": 195781, "self": 0.0, "children": { "worker_root": { "total": 5623.644753410855, "count": 195781, "is_parallel": true, "self": 2724.9925858025613, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018470899999556423, "count": 1, "is_parallel": true, "self": 0.0006573000000571483, "children": { "_process_rank_one_or_two_observation": { "total": 0.001189789999898494, "count": 8, "is_parallel": true, "self": 0.001189789999898494 } } }, "UnityEnvironment.step": { "total": 0.040352640000037354, "count": 1, "is_parallel": true, "self": 0.0003524039998410444, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031834300034461194, "count": 1, "is_parallel": true, "self": 0.00031834300034461194 }, "communicator.exchange": { "total": 0.03731206100019335, "count": 1, "is_parallel": true, "self": 0.03731206100019335 }, "steps_from_proto": { "total": 0.002369831999658345, "count": 1, "is_parallel": true, "self": 0.00023731999908704893, "children": { "_process_rank_one_or_two_observation": { "total": 0.002132512000571296, "count": 8, "is_parallel": true, "self": 0.002132512000571296 } } } } } } }, "UnityEnvironment.step": { "total": 2898.6521676082934, "count": 195780, "is_parallel": true, "self": 68.50199004686783, "children": { "UnityEnvironment._generate_step_input": { "total": 45.943571268686355, "count": 195780, "is_parallel": true, "self": 45.943571268686355 }, "communicator.exchange": { "total": 2592.501566384087, "count": 195780, "is_parallel": true, "self": 2592.501566384087 }, "steps_from_proto": { "total": 191.70503990865245, "count": 195780, "is_parallel": true, "self": 42.89309798299155, "children": { "_process_rank_one_or_two_observation": { "total": 148.8119419256609, "count": 1566240, "is_parallel": true, "self": 148.8119419256609 } } } } } } } } } } }, "trainer_advance": { "total": 1889.7049589658627, "count": 195781, "self": 10.335507277827219, "children": { "process_trajectory": { "total": 344.7558735940338, "count": 195781, "self": 344.26133466703413, "children": { "RLTrainer._checkpoint": { "total": 0.49453892699966673, "count": 6, "self": 0.49453892699966673 } } }, "_update_policy": { "total": 1534.6135780940017, "count": 1395, "self": 818.8176934640333, "children": { "TorchPPOOptimizer.update": { "total": 715.7958846299684, "count": 68448, "self": 715.7958846299684 } } } } } } }, "trainer_threads": { "total": 8.229999366449192e-07, "count": 1, "self": 8.229999366449192e-07 }, "TrainerController._save_models": { "total": 0.08436799599985534, "count": 1, "self": 0.0011335190001773299, "children": { "RLTrainer._checkpoint": { "total": 0.08323447699967801, "count": 1, "self": 0.08323447699967801 } } } } } } }