{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 1.4402799606323242, "min": 1.4402799606323242, "max": 1.4402799606323242, "count": 1 }, "Pyramids.Policy.Entropy.sum": { "value": 43692.33203125, "min": 43692.33203125, "max": 43692.33203125, "count": 1 }, "Pyramids.Step.mean": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Step.sum": { "value": 29952.0, "min": 29952.0, "max": 29952.0, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": -0.221921905875206, "min": -0.221921905875206, "max": -0.221921905875206, "count": 1 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": -52.59549331665039, "min": -52.59549331665039, "max": -52.59549331665039, "count": 1 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.4863353967666626, "min": 0.4863353967666626, "max": 0.4863353967666626, "count": 1 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 115.26148986816406, "min": 115.26148986816406, "max": 115.26148986816406, "count": 1 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07355356168899187, "min": 0.07355356168899187, "max": 0.07355356168899187, "count": 1 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.5148749318229431, "min": 0.5148749318229431, "max": 0.5148749318229431, "count": 1 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.00873875612131816, "min": 0.00873875612131816, "max": 0.00873875612131816, "count": 1 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.06117129284922712, "min": 0.06117129284922712, "max": 0.06117129284922712, "count": 1 }, "Pyramids.Policy.LearningRate.mean": { "value": 0.00029838354339596195, "min": 0.00029838354339596195, "max": 0.00029838354339596195, "count": 1 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0020886848037717336, "min": 0.0020886848037717336, "max": 0.0020886848037717336, "count": 1 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.19946118095238097, "min": 0.19946118095238097, "max": 0.19946118095238097, "count": 1 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.3962282666666668, "min": 1.3962282666666668, "max": 1.3962282666666668, "count": 1 }, "Pyramids.Policy.Beta.mean": { "value": 0.009946171977142856, "min": 0.009946171977142856, "max": 0.009946171977142856, "count": 1 }, "Pyramids.Policy.Beta.sum": { "value": 0.06962320384, "min": 0.06962320384, "max": 0.06962320384, "count": 1 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.5651363730430603, "min": 0.5651363730430603, "max": 0.5651363730430603, "count": 1 }, "Pyramids.Losses.RNDLoss.sum": { "value": 3.9559547901153564, "min": 3.9559547901153564, "max": 3.9559547901153564, "count": 1 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 1 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 15984.0, "min": 15984.0, "max": 15984.0, "count": 1 }, "Pyramids.Environment.CumulativeReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Environment.CumulativeReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": -1.0000000521540642, "min": -1.0000000521540642, "max": -1.0000000521540642, "count": 1 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": -16.000000834465027, "min": -16.000000834465027, "max": -16.000000834465027, "count": 1 }, "Pyramids.Policy.RndReward.mean": { "value": 12.426324671134353, "min": 12.426324671134353, "max": 12.426324671134353, "count": 1 }, "Pyramids.Policy.RndReward.sum": { "value": 198.82119473814964, "min": 198.82119473814964, "max": 198.82119473814964, "count": 1 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1724185621", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1724185774" }, "total": 152.73451457800002, "count": 1, "self": 0.6564099619999979, "children": { "run_training.setup": { "total": 0.07491729100001976, "count": 1, "self": 0.07491729100001976 }, "TrainerController.start_learning": { "total": 152.003187325, "count": 1, "self": 0.11504668400084483, "children": { "TrainerController._reset_env": { "total": 3.1649533120000797, "count": 1, "self": 3.1649533120000797 }, "TrainerController.advance": { "total": 148.3503989669989, "count": 3000, "self": 0.13388741599374043, "children": { "env_step": { "total": 91.04525362799791, "count": 3000, "self": 81.83397648699247, "children": { "SubprocessEnvManager._take_step": { "total": 9.137691959003405, "count": 3000, "self": 0.3984443300080329, "children": { "TorchPolicy.evaluate": { "total": 8.739247628995372, "count": 3000, "self": 8.739247628995372 } } }, "workers": { "total": 0.07358518200203434, "count": 2999, "self": 0.0, "children": { "worker_root": { "total": 151.09217432901232, "count": 2999, "is_parallel": true, "self": 79.17709236801352, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0040168009998069465, "count": 1, "is_parallel": true, "self": 0.0013484149999385409, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026683859998684056, "count": 8, "is_parallel": true, "self": 0.0026683859998684056 } } }, "UnityEnvironment.step": { "total": 0.08099046699999235, "count": 1, "is_parallel": true, "self": 0.0008831420000205981, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006552380000357516, "count": 1, "is_parallel": true, "self": 0.0006552380000357516 }, "communicator.exchange": { "total": 0.07697491199996875, "count": 1, "is_parallel": true, "self": 0.07697491199996875 }, "steps_from_proto": { "total": 0.0024771749999672465, "count": 1, "is_parallel": true, "self": 0.0005402839997259434, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019368910002413031, "count": 8, "is_parallel": true, "self": 0.0019368910002413031 } } } } } } }, "UnityEnvironment.step": { "total": 71.9150819609988, "count": 2998, "is_parallel": true, "self": 2.5661998550094722, "children": { "UnityEnvironment._generate_step_input": { "total": 1.6024147429957338, "count": 2998, "is_parallel": true, "self": 1.6024147429957338 }, "communicator.exchange": { "total": 61.08742125099525, "count": 2998, "is_parallel": true, "self": 61.08742125099525 }, "steps_from_proto": { "total": 6.65904611199835, "count": 2998, "is_parallel": true, "self": 1.4718150589978904, "children": { "_process_rank_one_or_two_observation": { "total": 5.18723105300046, "count": 23984, "is_parallel": true, "self": 5.18723105300046 } } } } } } } } } } }, "trainer_advance": { "total": 57.17125792300726, "count": 2999, "self": 0.16945724301353948, "children": { "process_trajectory": { "total": 8.388986830993417, "count": 2999, "self": 8.388986830993417 }, "_update_policy": { "total": 48.612813849000304, "count": 11, "self": 19.26792076600441, "children": { "TorchPPOOptimizer.update": { "total": 29.344893082995895, "count": 1038, "self": 29.344893082995895 } } } } } } }, "trainer_threads": { "total": 1.9170001905877143e-06, "count": 1, "self": 1.9170001905877143e-06 }, "TrainerController._save_models": { "total": 0.37278644499997426, "count": 1, "self": 0.006381074000046283, "children": { "RLTrainer._checkpoint": { "total": 0.366405370999928, "count": 1, "self": 0.366405370999928 } } } } } } }