{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.6166253089904785, "min": 2.6166253089904785, "max": 2.8903422355651855, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 26595.37890625, "min": 25114.3984375, "max": 29727.1640625, "count": 40 }, "SnowballTarget.Step.mean": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 2.035188913345337, "min": 0.06543982028961182, "max": 2.035188913345337, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 396.8618469238281, "min": 12.695324897766113, "max": 396.8618469238281, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 11.090909090909092, "min": 2.5636363636363635, "max": 11.218181818181819, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 488.0, "min": 120.0, "max": 617.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 11.090909090909092, "min": 2.5636363636363635, "max": 11.218181818181819, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 488.0, "min": 120.0, "max": 617.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0712768830509917, "min": 0.06915304061582568, "max": 0.07265863494481967, "count": 6 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.0712768830509917, "min": 0.06915304061582568, "max": 0.07265863494481967, "count": 6 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.26423525056021113, "min": 0.0920609251732531, "max": 0.26423525056021113, "count": 6 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.26423525056021113, "min": 0.0920609251732531, "max": 0.26423525056021113, "count": 6 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0660989780000026e-06, "min": 3.0660989780000026e-06, "max": 0.0002505660164780001, "count": 6 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.0660989780000026e-06, "min": 3.0660989780000026e-06, "max": 0.0002505660164780001, "count": 6 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10102199999999995, "min": 0.10102199999999995, "max": 0.18352199999999996, "count": 6 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10102199999999995, "min": 0.10102199999999995, "max": 0.18352199999999996, "count": 6 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.099780000000004e-05, "min": 6.099780000000004e-05, "max": 0.0041777478, "count": 6 }, "SnowballTarget.Policy.Beta.sum": { "value": 6.099780000000004e-05, "min": 6.099780000000004e-05, "max": 0.0041777478, "count": 6 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677076284", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --force --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1677077272" }, "total": 987.441850477, "count": 1, "self": 0.38259765699990567, "children": { "run_training.setup": { "total": 0.11054608599999938, "count": 1, "self": 0.11054608599999938 }, "TrainerController.start_learning": { "total": 986.9487067340001, "count": 1, "self": 1.1814164109872536, "children": { "TrainerController._reset_env": { "total": 6.032866755999976, "count": 1, "self": 6.032866755999976 }, "TrainerController.advance": { "total": 979.6170508790132, "count": 36403, "self": 0.5583066380155515, "children": { "env_step": { "total": 979.0587442409976, "count": 36403, "self": 737.9509035890554, "children": { "SubprocessEnvManager._take_step": { "total": 240.53268254596367, "count": 36403, "self": 3.3267687299653517, "children": { "TorchPolicy.evaluate": { "total": 237.20591381599831, "count": 36403, "self": 56.05418024799371, "children": { "TorchPolicy.sample_actions": { "total": 181.1517335680046, "count": 36403, "self": 181.1517335680046 } } } } }, "workers": { "total": 0.5751581059785167, "count": 36403, "self": 0.0, "children": { "worker_root": { "total": 984.1857254520095, "count": 36403, "is_parallel": true, "self": 496.85911151802145, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019560370000135663, "count": 1, "is_parallel": true, "self": 0.0007224139997106249, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012336230003029414, "count": 10, "is_parallel": true, "self": 0.0012336230003029414 } } }, "UnityEnvironment.step": { "total": 0.03456791999997222, "count": 1, "is_parallel": true, "self": 0.000356252999949902, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000303991999999198, "count": 1, "is_parallel": true, "self": 0.000303991999999198 }, "communicator.exchange": { "total": 0.032161796999957915, "count": 1, "is_parallel": true, "self": 0.032161796999957915 }, "steps_from_proto": { "total": 0.001745878000065204, "count": 1, "is_parallel": true, "self": 0.00039764600001035433, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013482320000548498, "count": 10, "is_parallel": true, "self": 0.0013482320000548498 } } } } } } }, "UnityEnvironment.step": { "total": 487.326613933988, "count": 36402, "is_parallel": true, "self": 19.653734838980768, "children": { "UnityEnvironment._generate_step_input": { "total": 10.787503225997511, "count": 36402, "is_parallel": true, "self": 10.787503225997511 }, "communicator.exchange": { "total": 392.9952968080147, "count": 36402, "is_parallel": true, "self": 392.9952968080147 }, "steps_from_proto": { "total": 63.89007906099505, "count": 36402, "is_parallel": true, "self": 13.888110268036144, "children": { "_process_rank_one_or_two_observation": { "total": 50.001968792958905, "count": 364020, "is_parallel": true, "self": 50.001968792958905 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00010757299992292246, "count": 1, "self": 0.00010757299992292246, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 968.4684696181288, "count": 1241972, "is_parallel": true, "self": 32.21537618312084, "children": { "process_trajectory": { "total": 745.2545512160078, "count": 1241972, "is_parallel": true, "self": 735.4877742590081, "children": { "RLTrainer._checkpoint": { "total": 9.766776956999706, "count": 40, "is_parallel": true, "self": 9.766776956999706 } } }, "_update_policy": { "total": 190.99854221900011, "count": 6, "is_parallel": true, "self": 105.12497627700964, "children": { "TorchPPOOptimizer.update": { "total": 85.87356594199048, "count": 9267, "is_parallel": true, "self": 85.87356594199048 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11726511499978187, "count": 1, "self": 0.0012120519998006785, "children": { "RLTrainer._checkpoint": { "total": 0.1160530629999812, "count": 1, "self": 0.1160530629999812 } } } } } } }