{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4000111818313599, "min": 1.4000111818313599, "max": 1.4265395402908325, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70489.1640625, "min": 68261.8203125, "max": 78717.390625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 73.91017964071857, "min": 70.24501424501425, "max": 407.2903225806452, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49372.0, "min": 49242.0, "max": 50504.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999951.0, "min": 49878.0, "max": 1999951.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999951.0, "min": 49878.0, "max": 1999951.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.452033758163452, "min": 0.032783374190330505, "max": 2.5400776863098145, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1637.95849609375, "min": 4.032354831695557, "max": 1736.4808349609375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8492462703746235, "min": 1.7706257155755671, "max": 4.040511085822122, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2571.2965086102486, "min": 217.78696301579475, "max": 2725.0666291713715, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8492462703746235, "min": 1.7706257155755671, "max": 4.040511085822122, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2571.2965086102486, "min": 217.78696301579475, "max": 2725.0666291713715, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017331657956108557, "min": 0.01313978845270564, "max": 0.019939769353853384, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05199497386832567, "min": 0.02627957690541128, "max": 0.056694652958928296, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06100028339359495, "min": 0.02230094503611326, "max": 0.062472572550177574, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18300085018078485, "min": 0.04460189007222652, "max": 0.18741771765053272, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.687548770850002e-06, "min": 3.687548770850002e-06, "max": 0.0002953500765499749, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1062646312550006e-05, "min": 1.1062646312550006e-05, "max": 0.0008437926187358, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10122915000000003, "min": 0.10122915000000003, "max": 0.19845002500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036874500000001, "min": 0.20762144999999999, "max": 0.5812641999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.133458500000005e-05, "min": 7.133458500000005e-05, "max": 0.004922656247499998, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021400375500000015, "min": 0.00021400375500000015, "max": 0.014065083579999998, "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": "1712913560", "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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712917641" }, "total": 4080.818327191, "count": 1, "self": 0.7033262140007537, "children": { "run_training.setup": { "total": 0.06379801299999599, "count": 1, "self": 0.06379801299999599 }, "TrainerController.start_learning": { "total": 4080.0512029639995, "count": 1, "self": 7.293523076938072, "children": { "TrainerController._reset_env": { "total": 2.960698817999969, "count": 1, "self": 2.960698817999969 }, "TrainerController.advance": { "total": 4069.6743772820623, "count": 233656, "self": 7.276517322972268, "children": { "env_step": { "total": 2650.3707821411795, "count": 233656, "self": 2228.8102507961667, "children": { "SubprocessEnvManager._take_step": { "total": 416.77226434999204, "count": 233656, "self": 25.966085310899473, "children": { "TorchPolicy.evaluate": { "total": 390.80617903909257, "count": 223014, "self": 390.80617903909257 } } }, "workers": { "total": 4.788266995020649, "count": 233656, "self": 0.0, "children": { "worker_root": { "total": 4067.1191805692506, "count": 233656, "is_parallel": true, "self": 2302.6108244212514, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010779510000133996, "count": 1, "is_parallel": true, "self": 0.00022884000003386973, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008491109999795299, "count": 2, "is_parallel": true, "self": 0.0008491109999795299 } } }, "UnityEnvironment.step": { "total": 0.03414810200001739, "count": 1, "is_parallel": true, "self": 0.00043108800002755743, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017268800002057105, "count": 1, "is_parallel": true, "self": 0.00017268800002057105 }, "communicator.exchange": { "total": 0.03266250599995146, "count": 1, "is_parallel": true, "self": 0.03266250599995146 }, "steps_from_proto": { "total": 0.0008818200000177967, "count": 1, "is_parallel": true, "self": 0.00022746900003767223, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006543509999801245, "count": 2, "is_parallel": true, "self": 0.0006543509999801245 } } } } } } }, "UnityEnvironment.step": { "total": 1764.5083561479992, "count": 233655, "is_parallel": true, "self": 56.67541392177736, "children": { "UnityEnvironment._generate_step_input": { "total": 88.20896352902491, "count": 233655, "is_parallel": true, "self": 88.20896352902491 }, "communicator.exchange": { "total": 1489.4299386581285, "count": 233655, "is_parallel": true, "self": 1489.4299386581285 }, "steps_from_proto": { "total": 130.19404003906823, "count": 233655, "is_parallel": true, "self": 43.20270010420734, "children": { "_process_rank_one_or_two_observation": { "total": 86.99133993486089, "count": 467310, "is_parallel": true, "self": 86.99133993486089 } } } } } } } } } } }, "trainer_advance": { "total": 1412.0270778179104, "count": 233656, "self": 10.731404199878625, "children": { "process_trajectory": { "total": 234.16093517803398, "count": 233656, "self": 232.97462485003433, "children": { "RLTrainer._checkpoint": { "total": 1.1863103279996494, "count": 10, "self": 1.1863103279996494 } } }, "_update_policy": { "total": 1167.1347384399978, "count": 97, "self": 309.743579498994, "children": { "TorchPPOOptimizer.update": { "total": 857.3911589410038, "count": 2910, "self": 857.3911589410038 } } } } } } }, "trainer_threads": { "total": 1.3729995771427639e-06, "count": 1, "self": 1.3729995771427639e-06 }, "TrainerController._save_models": { "total": 0.12260241399962979, "count": 1, "self": 0.006169661000058113, "children": { "RLTrainer._checkpoint": { "total": 0.11643275299957168, "count": 1, "self": 0.11643275299957168 } } } } } } }