{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4042266607284546, "min": 1.4042266607284546, "max": 1.4274191856384277, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71635.21875, "min": 69265.2578125, "max": 76980.5, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 86.06608695652174, "min": 74.3499245852187, "max": 380.87786259541986, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49488.0, "min": 48707.0, "max": 50077.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999987.0, "min": 49635.0, "max": 1999987.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999987.0, "min": 49635.0, "max": 1999987.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.463456869125366, "min": 0.1470765471458435, "max": 2.4849486351013184, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1416.4876708984375, "min": 19.119951248168945, "max": 1623.906005859375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.827055808461231, "min": 1.9481795384333684, "max": 3.9760772171059275, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2200.5570898652077, "min": 253.2633399963379, "max": 2513.690305054188, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.827055808461231, "min": 1.9481795384333684, "max": 3.9760772171059275, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2200.5570898652077, "min": 253.2633399963379, "max": 2513.690305054188, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016120954238188764, "min": 0.013608071289602069, "max": 0.021099030579595515, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04836286271456629, "min": 0.027822340273996816, "max": 0.06262276646836351, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05203762989905145, "min": 0.02262524977947275, "max": 0.06217325385659933, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15611288969715437, "min": 0.0452504995589455, "max": 0.18087040558457373, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6040987986666742e-06, "min": 3.6040987986666742e-06, "max": 0.0002953488015504, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0812296396000023e-05, "min": 1.0812296396000023e-05, "max": 0.0008439657186781, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120133333333331, "min": 0.10120133333333331, "max": 0.1984496, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30360399999999993, "min": 0.2075538, "max": 0.5813219, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.994653333333345e-05, "min": 6.994653333333345e-05, "max": 0.0049226350400000006, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020983960000000036, "min": 0.00020983960000000036, "max": 0.014067962809999997, "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": "1754498334", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1754500693" }, "total": 2358.8398496070004, "count": 1, "self": 0.4520827720007219, "children": { "run_training.setup": { "total": 0.03201667100006489, "count": 1, "self": 0.03201667100006489 }, "TrainerController.start_learning": { "total": 2358.355750164, "count": 1, "self": 4.138303037131209, "children": { "TrainerController._reset_env": { "total": 3.917524260999926, "count": 1, "self": 3.917524260999926 }, "TrainerController.advance": { "total": 2350.194489155869, "count": 233378, "self": 4.327267765654597, "children": { "env_step": { "total": 1868.6319110470986, "count": 233378, "self": 1482.1768687472959, "children": { "SubprocessEnvManager._take_step": { "total": 383.82158530583206, "count": 233378, "self": 14.304672833769018, "children": { "TorchPolicy.evaluate": { "total": 369.51691247206304, "count": 223052, "self": 369.51691247206304 } } }, "workers": { "total": 2.63345699397064, "count": 233378, "self": 0.0, "children": { "worker_root": { "total": 2351.0832348779827, "count": 233378, "is_parallel": true, "self": 1140.916713117008, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009433919999537466, "count": 1, "is_parallel": true, "self": 0.00026271100000485603, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006806809999488905, "count": 2, "is_parallel": true, "self": 0.0006806809999488905 } } }, "UnityEnvironment.step": { "total": 0.05569983800000955, "count": 1, "is_parallel": true, "self": 0.0005984529998386279, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020349800001895346, "count": 1, "is_parallel": true, "self": 0.00020349800001895346 }, "communicator.exchange": { "total": 0.054157498999984455, "count": 1, "is_parallel": true, "self": 0.054157498999984455 }, "steps_from_proto": { "total": 0.0007403880001675134, "count": 1, "is_parallel": true, "self": 0.00022292400012702274, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005174640000404906, "count": 2, "is_parallel": true, "self": 0.0005174640000404906 } } } } } } }, "UnityEnvironment.step": { "total": 1210.1665217609748, "count": 233377, "is_parallel": true, "self": 36.63153632113017, "children": { "UnityEnvironment._generate_step_input": { "total": 78.02485292190931, "count": 233377, "is_parallel": true, "self": 78.02485292190931 }, "communicator.exchange": { "total": 1010.7865471359391, "count": 233377, "is_parallel": true, "self": 1010.7865471359391 }, "steps_from_proto": { "total": 84.72358538199614, "count": 233377, "is_parallel": true, "self": 29.584028842238013, "children": { "_process_rank_one_or_two_observation": { "total": 55.13955653975813, "count": 466754, "is_parallel": true, "self": 55.13955653975813 } } } } } } } } } } }, "trainer_advance": { "total": 477.23531034311577, "count": 233378, "self": 6.116224807999515, "children": { "process_trajectory": { "total": 152.69629766011826, "count": 233378, "self": 151.52351855911888, "children": { "RLTrainer._checkpoint": { "total": 1.172779100999378, "count": 10, "self": 1.172779100999378 } } }, "_update_policy": { "total": 318.422787874998, "count": 97, "self": 253.87250097099763, "children": { "TorchPPOOptimizer.update": { "total": 64.55028690400036, "count": 2910, "self": 64.55028690400036 } } } } } } }, "trainer_threads": { "total": 8.739998520468362e-07, "count": 1, "self": 8.739998520468362e-07 }, "TrainerController._save_models": { "total": 0.10543283599963615, "count": 1, "self": 0.0015529899992543506, "children": { "RLTrainer._checkpoint": { "total": 0.1038798460003818, "count": 1, "self": 0.1038798460003818 } } } } } } }