{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.15132513642311096, "min": 0.14829126000404358, "max": 1.4613839387893677, "count": 100 }, "Pyramids.Policy.Entropy.sum": { "value": 4484.06640625, "min": 4429.75634765625, "max": 44332.54296875, "count": 100 }, "Pyramids.Step.mean": { "value": 2999905.0, "min": 29952.0, "max": 2999905.0, "count": 100 }, "Pyramids.Step.sum": { "value": 2999905.0, "min": 29952.0, "max": 2999905.0, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.8932382464408875, "min": -0.15844400227069855, "max": 0.9028961062431335, "count": 100 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 273.3309020996094, "min": -37.55122756958008, "max": 283.5093688964844, "count": 100 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0026990168262273073, "min": -0.0904218927025795, "max": 0.44351574778556824, "count": 100 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.8258991241455078, "min": -24.775598526000977, "max": 105.11323547363281, "count": 100 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07123220952191679, "min": 0.0634671286804535, "max": 0.07412307414675265, "count": 100 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.997250933306835, "min": 0.5111616581674041, "max": 1.0950732377025783, "count": 100 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.014199982696611968, "min": 0.0015536344187114487, "max": 0.01738580065527155, "count": 100 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.19879975775256756, "min": 0.01145576259164202, "max": 0.2434012091738017, "count": 100 }, "Pyramids.Policy.LearningRate.mean": { "value": 1.5668494777500004e-06, "min": 1.5668494777500004e-06, "max": 0.00029838354339596195, "count": 100 }, "Pyramids.Policy.LearningRate.sum": { "value": 2.1935892688500007e-05, "min": 2.1935892688500007e-05, "max": 0.0039822694725769, "count": 100 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10052225000000001, "min": 0.10052225000000001, "max": 0.19946118095238097, "count": 100 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4073115, "min": 1.3897045333333333, "max": 2.8274231, "count": 100 }, "Pyramids.Policy.Beta.mean": { "value": 6.217277500000003e-05, "min": 6.217277500000003e-05, "max": 0.009946171977142856, "count": 100 }, "Pyramids.Policy.Beta.sum": { "value": 0.0008704188500000005, "min": 0.0008704188500000005, "max": 0.13275956769, "count": 100 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.008727065287530422, "min": 0.008441923186182976, "max": 0.5478127598762512, "count": 100 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12217891961336136, "min": 0.11818692088127136, "max": 3.834689140319824, "count": 100 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 192.46794871794873, "min": 192.46794871794873, "max": 999.0, "count": 100 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30025.0, "min": 15984.0, "max": 32492.0, "count": 100 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.7818820366206078, "min": -1.0000000521540642, "max": 1.8058783713023405, "count": 100 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 277.9735977128148, "min": -32.000001668930054, "max": 277.9735977128148, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.7818820366206078, "min": -1.0000000521540642, "max": 1.8058783713023405, "count": 100 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 277.9735977128148, "min": -32.000001668930054, "max": 277.9735977128148, "count": 100 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0174046519315221, "min": 0.0174046519315221, "max": 10.561767938546836, "count": 100 }, "Pyramids.Policy.RndReward.sum": { "value": 2.7151257013174472, "min": 2.610588401039422, "max": 168.98828701674938, "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": "1728245780", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1728253295" }, "total": 7515.151601063999, "count": 1, "self": 0.7015553429991996, "children": { "run_training.setup": { "total": 0.06040649500027939, "count": 1, "self": 0.06040649500027939 }, "TrainerController.start_learning": { "total": 7514.389639225999, "count": 1, "self": 4.048271164157995, "children": { "TrainerController._reset_env": { "total": 1.9362581060004231, "count": 1, "self": 1.9362581060004231 }, "TrainerController.advance": { "total": 7508.33986325284, "count": 195976, "self": 4.074849193856608, "children": { "env_step": { "total": 5169.692394295765, "count": 195976, "self": 4883.823563641801, "children": { "SubprocessEnvManager._take_step": { "total": 283.5451569709858, "count": 195976, "self": 13.301667460987119, "children": { "TorchPolicy.evaluate": { "total": 270.24348950999865, "count": 187548, "self": 270.24348950999865 } } }, "workers": { "total": 2.323673682977187, "count": 195976, "self": 0.0, "children": { "worker_root": { "total": 7499.651430609375, "count": 195976, "is_parallel": true, "self": 2970.239232542388, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003996958999778144, "count": 1, "is_parallel": true, "self": 0.0015623619997313654, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024345970000467787, "count": 8, "is_parallel": true, "self": 0.0024345970000467787 } } }, "UnityEnvironment.step": { "total": 0.05505172799985303, "count": 1, "is_parallel": true, "self": 0.0006405429999176704, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000466280999717128, "count": 1, "is_parallel": true, "self": 0.000466280999717128 }, "communicator.exchange": { "total": 0.05208536300006017, "count": 1, "is_parallel": true, "self": 0.05208536300006017 }, "steps_from_proto": { "total": 0.0018595410001580603, "count": 1, "is_parallel": true, "self": 0.0004083490007360524, "children": { "_process_rank_one_or_two_observation": { "total": 0.001451191999422008, "count": 8, "is_parallel": true, "self": 0.001451191999422008 } } } } } } }, "UnityEnvironment.step": { "total": 4529.412198066987, "count": 195975, "is_parallel": true, "self": 98.2967083275671, "children": { "UnityEnvironment._generate_step_input": { "total": 67.10695057191242, "count": 195975, "is_parallel": true, "self": 67.10695057191242 }, "communicator.exchange": { "total": 4081.935213690756, "count": 195975, "is_parallel": true, "self": 4081.935213690756 }, "steps_from_proto": { "total": 282.07332547675196, "count": 195975, "is_parallel": true, "self": 56.58310297766775, "children": { "_process_rank_one_or_two_observation": { "total": 225.4902224990842, "count": 1567800, "is_parallel": true, "self": 225.4902224990842 } } } } } } } } } } }, "trainer_advance": { "total": 2334.572619763219, "count": 195976, "self": 8.00400231726735, "children": { "process_trajectory": { "total": 386.8590042699602, "count": 195976, "self": 386.37888462595856, "children": { "RLTrainer._checkpoint": { "total": 0.4801196440016611, "count": 6, "self": 0.4801196440016611 } } }, "_update_policy": { "total": 1939.7096131759913, "count": 1391, "self": 830.3642280660961, "children": { "TorchPPOOptimizer.update": { "total": 1109.3453851098952, "count": 68427, "self": 1109.3453851098952 } } } } } } }, "trainer_threads": { "total": 1.329000951955095e-06, "count": 1, "self": 1.329000951955095e-06 }, "TrainerController._save_models": { "total": 0.06524537400036934, "count": 1, "self": 0.0018215420004707994, "children": { "RLTrainer._checkpoint": { "total": 0.06342383199989854, "count": 1, "self": 0.06342383199989854 } } } } } } }