{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4067308902740479, "min": 1.4067308902740479, "max": 1.427574634552002, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70610.859375, "min": 67883.3359375, "max": 78433.1953125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.98032786885246, "min": 80.98032786885246, "max": 413.91735537190084, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49398.0, "min": 48890.0, "max": 50185.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999987.0, "min": 49556.0, "max": 1999987.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999987.0, "min": 49556.0, "max": 1999987.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4015870094299316, "min": 0.1119094118475914, "max": 2.5020134449005127, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1464.9681396484375, "min": 13.429129600524902, "max": 1464.9681396484375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.760661267452553, "min": 1.9653475438555081, "max": 3.953518480826647, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2294.003373146057, "min": 235.84170526266098, "max": 2294.003373146057, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.760661267452553, "min": 1.9653475438555081, "max": 3.953518480826647, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2294.003373146057, "min": 235.84170526266098, "max": 2294.003373146057, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01535719070622387, "min": 0.013121664045259725, "max": 0.01884475287733949, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04607157211867161, "min": 0.02624332809051945, "max": 0.054697395723390704, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.062165374226040314, "min": 0.02248382301380237, "max": 0.062165374226040314, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18649612267812093, "min": 0.04496764602760474, "max": 0.18649612267812093, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3132488956166653e-06, "min": 3.3132488956166653e-06, "max": 0.00029537212654262503, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.939746686849996e-06, "min": 9.939746686849996e-06, "max": 0.0008441673186109002, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10110438333333334, "min": 0.10110438333333334, "max": 0.19845737500000007, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30331315000000003, "min": 0.20735125, "max": 0.5813891000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.51087283333333e-05, "min": 6.51087283333333e-05, "max": 0.004923023012500002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019532618499999992, "min": 0.00019532618499999992, "max": 0.014071316089999997, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1752155643", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1752158107" }, "total": 2463.381691095, "count": 1, "self": 0.39258906199984267, "children": { "run_training.setup": { "total": 0.02350251899997602, "count": 1, "self": 0.02350251899997602 }, "TrainerController.start_learning": { "total": 2462.965599514, "count": 1, "self": 4.087009010024303, "children": { "TrainerController._reset_env": { "total": 3.0782461439999906, "count": 1, "self": 3.0782461439999906 }, "TrainerController.advance": { "total": 2455.701693771976, "count": 232118, "self": 4.433572092890699, "children": { "env_step": { "total": 1949.3338366430048, "count": 232118, "self": 1549.8410731288905, "children": { "SubprocessEnvManager._take_step": { "total": 396.8839038180507, "count": 232118, "self": 15.068302473955555, "children": { "TorchPolicy.evaluate": { "total": 381.81560134409517, "count": 222883, "self": 381.81560134409517 } } }, "workers": { "total": 2.608859696063746, "count": 232118, "self": 0.0, "children": { "worker_root": { "total": 2455.7303042769263, "count": 232118, "is_parallel": true, "self": 1186.8302322309814, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009335100000953389, "count": 1, "is_parallel": true, "self": 0.00024297900006331474, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006905310000320242, "count": 2, "is_parallel": true, "self": 0.0006905310000320242 } } }, "UnityEnvironment.step": { "total": 0.029119570999910138, "count": 1, "is_parallel": true, "self": 0.00033046699991245987, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019544299993867753, "count": 1, "is_parallel": true, "self": 0.00019544299993867753 }, "communicator.exchange": { "total": 0.027933950000033292, "count": 1, "is_parallel": true, "self": 0.027933950000033292 }, "steps_from_proto": { "total": 0.0006597110000257089, "count": 1, "is_parallel": true, "self": 0.0001729100000602557, "children": { "_process_rank_one_or_two_observation": { "total": 0.00048680099996545323, "count": 2, "is_parallel": true, "self": 0.00048680099996545323 } } } } } } }, "UnityEnvironment.step": { "total": 1268.9000720459449, "count": 232117, "is_parallel": true, "self": 37.12125597508111, "children": { "UnityEnvironment._generate_step_input": { "total": 82.07948878902107, "count": 232117, "is_parallel": true, "self": 82.07948878902107 }, "communicator.exchange": { "total": 1061.077534370902, "count": 232117, "is_parallel": true, "self": 1061.077534370902 }, "steps_from_proto": { "total": 88.6217929109406, "count": 232117, "is_parallel": true, "self": 32.84149776994616, "children": { "_process_rank_one_or_two_observation": { "total": 55.78029514099444, "count": 464234, "is_parallel": true, "self": 55.78029514099444 } } } } } } } } } } }, "trainer_advance": { "total": 501.93428503608027, "count": 232118, "self": 6.446085728059984, "children": { "process_trajectory": { "total": 155.1991779380204, "count": 232118, "self": 154.09808825401967, "children": { "RLTrainer._checkpoint": { "total": 1.1010896840007263, "count": 10, "self": 1.1010896840007263 } } }, "_update_policy": { "total": 340.2890213699999, "count": 97, "self": 276.608247363022, "children": { "TorchPPOOptimizer.update": { "total": 63.68077400697791, "count": 2910, "self": 63.68077400697791 } } } } } } }, "trainer_threads": { "total": 1.0070002645079512e-06, "count": 1, "self": 1.0070002645079512e-06 }, "TrainerController._save_models": { "total": 0.09864958099979049, "count": 1, "self": 0.0014910219997545937, "children": { "RLTrainer._checkpoint": { "total": 0.0971585590000359, "count": 1, "self": 0.0971585590000359 } } } } } } }