{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.409096121788025, "min": 1.409096121788025, "max": 1.430606484413147, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69707.984375, "min": 68221.1484375, "max": 77315.3671875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 73.60059612518629, "min": 73.58805970149254, "max": 428.864406779661, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49386.0, "min": 49192.0, "max": 50606.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999973.0, "min": 49974.0, "max": 1999973.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999973.0, "min": 49974.0, "max": 1999973.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.482327938079834, "min": 0.13443289697170258, "max": 2.5390899181365967, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1665.64208984375, "min": 15.72864818572998, "max": 1687.0552978515625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8302006981767236, "min": 1.8936435827332685, "max": 3.9796446329187076, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2570.0646684765816, "min": 221.5562991797924, "max": 2598.035621225834, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8302006981767236, "min": 1.8936435827332685, "max": 3.9796446329187076, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2570.0646684765816, "min": 221.5562991797924, "max": 2598.035621225834, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017265411100359215, "min": 0.012782630754615335, "max": 0.020003824642238516, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.051796233301077646, "min": 0.02556526150923067, "max": 0.05599940132039288, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06207490575810274, "min": 0.021207097483177978, "max": 0.06308400088714228, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18622471727430823, "min": 0.042414194966355956, "max": 0.18925200266142683, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.831098722999997e-06, "min": 3.831098722999997e-06, "max": 0.000295322176559275, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.149329616899999e-05, "min": 1.149329616899999e-05, "max": 0.0008440164186612001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10127700000000002, "min": 0.10127700000000002, "max": 0.19844072500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3038310000000001, "min": 0.2077038, "max": 0.5813387999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.372229999999994e-05, "min": 7.372229999999994e-05, "max": 0.004922192177500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002211668999999998, "min": 0.0002211668999999998, "max": 0.01406880612, "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": "1701605667", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701608105" }, "total": 2437.456198027, "count": 1, "self": 0.4908106109996879, "children": { "run_training.setup": { "total": 0.08575669700007893, "count": 1, "self": 0.08575669700007893 }, "TrainerController.start_learning": { "total": 2436.879630719, "count": 1, "self": 4.416979930055277, "children": { "TrainerController._reset_env": { "total": 3.9030968150000263, "count": 1, "self": 3.9030968150000263 }, "TrainerController.advance": { "total": 2428.4565060169452, "count": 233148, "self": 4.933418553694537, "children": { "env_step": { "total": 1910.0112413481952, "count": 233148, "self": 1581.7261517212391, "children": { "SubprocessEnvManager._take_step": { "total": 325.3682401779795, "count": 233148, "self": 17.25082555593542, "children": { "TorchPolicy.evaluate": { "total": 308.11741462204407, "count": 222936, "self": 308.11741462204407 } } }, "workers": { "total": 2.916849448976677, "count": 233148, "self": 0.0, "children": { "worker_root": { "total": 2429.3345482940313, "count": 233148, "is_parallel": true, "self": 1145.9426218900971, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010646609999866996, "count": 1, "is_parallel": true, "self": 0.00033167300000513933, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007329879999815603, "count": 2, "is_parallel": true, "self": 0.0007329879999815603 } } }, "UnityEnvironment.step": { "total": 0.031072577000031743, "count": 1, "is_parallel": true, "self": 0.0003206559999853198, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021292700000685727, "count": 1, "is_parallel": true, "self": 0.00021292700000685727 }, "communicator.exchange": { "total": 0.02983953399996153, "count": 1, "is_parallel": true, "self": 0.02983953399996153 }, "steps_from_proto": { "total": 0.0006994600000780338, "count": 1, "is_parallel": true, "self": 0.00020022400008201657, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004992359999960172, "count": 2, "is_parallel": true, "self": 0.0004992359999960172 } } } } } } }, "UnityEnvironment.step": { "total": 1283.3919264039341, "count": 233147, "is_parallel": true, "self": 39.56576392912211, "children": { "UnityEnvironment._generate_step_input": { "total": 82.99597174292728, "count": 233147, "is_parallel": true, "self": 82.99597174292728 }, "communicator.exchange": { "total": 1071.221812059866, "count": 233147, "is_parallel": true, "self": 1071.221812059866 }, "steps_from_proto": { "total": 89.60837867201883, "count": 233147, "is_parallel": true, "self": 31.527304044954008, "children": { "_process_rank_one_or_two_observation": { "total": 58.08107462706482, "count": 466294, "is_parallel": true, "self": 58.08107462706482 } } } } } } } } } } }, "trainer_advance": { "total": 513.5118461150553, "count": 233148, "self": 6.710907937091065, "children": { "process_trajectory": { "total": 159.73232578096565, "count": 233148, "self": 158.69617057096627, "children": { "RLTrainer._checkpoint": { "total": 1.0361552099993787, "count": 10, "self": 1.0361552099993787 } } }, "_update_policy": { "total": 347.06861239699856, "count": 97, "self": 283.1210690669915, "children": { "TorchPPOOptimizer.update": { "total": 63.94754333000708, "count": 2910, "self": 63.94754333000708 } } } } } } }, "trainer_threads": { "total": 1.0899998414970469e-06, "count": 1, "self": 1.0899998414970469e-06 }, "TrainerController._save_models": { "total": 0.10304686699964805, "count": 1, "self": 0.0015749909998703515, "children": { "RLTrainer._checkpoint": { "total": 0.1014718759997777, "count": 1, "self": 0.1014718759997777 } } } } } } }