{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3739411234855652, "min": 0.3739411234855652, "max": 1.5047718286514282, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 11200.2841796875, "min": 11200.2841796875, "max": 45648.7578125, "count": 33 }, "Pyramids.Step.mean": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989928.0, "min": 29952.0, "max": 989928.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6031209230422974, "min": -0.10538581758737564, "max": 0.6545706391334534, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 170.08010864257812, "min": -25.397981643676758, "max": 183.27978515625, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.007571254391223192, "min": -0.021212035790085793, "max": 0.4121011197566986, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 2.1350936889648438, "min": -5.812098026275635, "max": 97.66796875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06601344463286093, "min": 0.06590305171786943, "max": 0.07301525055195324, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.990201669492914, "min": 0.5111067538636727, "max": 1.033990620885971, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.015789575056017687, "min": 0.0003668796064034191, "max": 0.016519466483476294, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.23684362584026533, "min": 0.00403567567043761, "max": 0.23684362584026533, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.469217510293336e-06, "min": 7.469217510293336e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011203826265440003, "min": 0.00011203826265440003, "max": 0.0031444331518556993, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248970666666667, "min": 0.10248970666666667, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373456, "min": 1.3886848, "max": 2.4428719, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025872169600000004, "min": 0.00025872169600000004, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003880825440000001, "min": 0.003880825440000001, "max": 0.10483961556999999, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01223546639084816, "min": 0.01223546639084816, "max": 0.399586945772171, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.1835319995880127, "min": 0.17160239815711975, "max": 2.7971086502075195, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 337.42857142857144, "min": 307.8695652173913, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30706.0, "min": 15984.0, "max": 33042.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6185666473375426, "min": -1.0000000521540642, "max": 1.6921304154979147, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 145.67099826037884, "min": -31.99760165810585, "max": 162.71319769322872, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6185666473375426, "min": -1.0000000521540642, "max": 1.6921304154979147, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 145.67099826037884, "min": -31.99760165810585, "max": 162.71319769322872, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.042794016491906305, "min": 0.03934783413063522, "max": 8.62995847966522, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8514614842715673, "min": 3.6200007400184404, "max": 138.07933567464352, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684301152", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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 Training --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": "1684303342" }, "total": 2189.97745116, "count": 1, "self": 0.78913496999985, "children": { "run_training.setup": { "total": 0.03847691000009945, "count": 1, "self": 0.03847691000009945 }, "TrainerController.start_learning": { "total": 2189.14983928, "count": 1, "self": 1.407952127954104, "children": { "TrainerController._reset_env": { "total": 3.7742672700001094, "count": 1, "self": 3.7742672700001094 }, "TrainerController.advance": { "total": 2183.824237406046, "count": 63930, "self": 1.372887170903141, "children": { "env_step": { "total": 1562.2141009810357, "count": 63930, "self": 1455.0789518310191, "children": { "SubprocessEnvManager._take_step": { "total": 106.31793980702514, "count": 63930, "self": 4.631091964018879, "children": { "TorchPolicy.evaluate": { "total": 101.68684784300626, "count": 62570, "self": 101.68684784300626 } } }, "workers": { "total": 0.8172093429914185, "count": 63930, "self": 0.0, "children": { "worker_root": { "total": 2184.095313795957, "count": 63930, "is_parallel": true, "self": 839.8432322699473, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017222149999724934, "count": 1, "is_parallel": true, "self": 0.0005202659997394221, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012019490002330713, "count": 8, "is_parallel": true, "self": 0.0012019490002330713 } } }, "UnityEnvironment.step": { "total": 0.04694044899997607, "count": 1, "is_parallel": true, "self": 0.0005485209997004858, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004552560001229722, "count": 1, "is_parallel": true, "self": 0.0004552560001229722 }, "communicator.exchange": { "total": 0.04408987600004366, "count": 1, "is_parallel": true, "self": 0.04408987600004366 }, "steps_from_proto": { "total": 0.0018467960001089523, "count": 1, "is_parallel": true, "self": 0.0004018269996777235, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014449690004312288, "count": 8, "is_parallel": true, "self": 0.0014449690004312288 } } } } } } }, "UnityEnvironment.step": { "total": 1344.2520815260095, "count": 63929, "is_parallel": true, "self": 32.79690609611566, "children": { "UnityEnvironment._generate_step_input": { "total": 22.227647016948822, "count": 63929, "is_parallel": true, "self": 22.227647016948822 }, "communicator.exchange": { "total": 1189.3575596429969, "count": 63929, "is_parallel": true, "self": 1189.3575596429969 }, "steps_from_proto": { "total": 99.86996876994817, "count": 63929, "is_parallel": true, "self": 19.788308064037437, "children": { "_process_rank_one_or_two_observation": { "total": 80.08166070591074, "count": 511432, "is_parallel": true, "self": 80.08166070591074 } } } } } } } } } } }, "trainer_advance": { "total": 620.2372492541072, "count": 63930, "self": 2.5969638241110715, "children": { "process_trajectory": { "total": 105.65010969499258, "count": 63930, "self": 105.38112108899236, "children": { "RLTrainer._checkpoint": { "total": 0.2689886060002209, "count": 2, "self": 0.2689886060002209 } } }, "_update_policy": { "total": 511.9901757350035, "count": 442, "self": 330.19687346101364, "children": { "TorchPPOOptimizer.update": { "total": 181.79330227398987, "count": 22827, "self": 181.79330227398987 } } } } } } }, "trainer_threads": { "total": 1.234999672306003e-06, "count": 1, "self": 1.234999672306003e-06 }, "TrainerController._save_models": { "total": 0.1433812410000428, "count": 1, "self": 0.0018343860001550638, "children": { "RLTrainer._checkpoint": { "total": 0.14154685499988773, "count": 1, "self": 0.14154685499988773 } } } } } } }