{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3988898992538452, "min": 1.3988898992538452, "max": 1.4257984161376953, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68872.9453125, "min": 68854.0390625, "max": 75697.890625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 76.31221020092735, "min": 75.01369863013699, "max": 412.5, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49374.0, "min": 48755.0, "max": 50325.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999971.0, "min": 49917.0, "max": 1999971.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999971.0, "min": 49917.0, "max": 1999971.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.406062602996826, "min": 0.08514009416103363, "max": 2.511354446411133, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1556.7225341796875, "min": 10.30195140838623, "max": 1573.681396484375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7621873946057223, "min": 1.758524002122485, "max": 4.040442948668233, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2434.135244309902, "min": 212.78140425682068, "max": 2505.074628174305, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7621873946057223, "min": 1.758524002122485, "max": 4.040442948668233, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2434.135244309902, "min": 212.78140425682068, "max": 2505.074628174305, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016998254233880693, "min": 0.013207156444817278, "max": 0.02009145899889215, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05099476270164208, "min": 0.026414312889634556, "max": 0.0568898291424072, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.062151126646333266, "min": 0.022699995587269463, "max": 0.06249258282283941, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1864533799389998, "min": 0.045399991174538926, "max": 0.1864533799389998, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4110988629999975e-06, "min": 3.4110988629999975e-06, "max": 0.0002953202265599249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0233296588999993e-05, "min": 1.0233296588999993e-05, "max": 0.0008440821186393, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10113700000000002, "min": 0.10113700000000002, "max": 0.19844007500000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30341100000000004, "min": 0.20740864999999992, "max": 0.5813607000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.673629999999995e-05, "min": 6.673629999999995e-05, "max": 0.004922159742500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020020889999999985, "min": 0.00020020889999999985, "max": 0.014069898930000001, "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": "1727362971", "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727365502" }, "total": 2530.826750928, "count": 1, "self": 0.42585493199976554, "children": { "run_training.setup": { "total": 0.07648481199998969, "count": 1, "self": 0.07648481199998969 }, "TrainerController.start_learning": { "total": 2530.3244111840004, "count": 1, "self": 4.532771957045043, "children": { "TrainerController._reset_env": { "total": 2.631052189000002, "count": 1, "self": 2.631052189000002 }, "TrainerController.advance": { "total": 2523.051314986955, "count": 232521, "self": 4.862948589955522, "children": { "env_step": { "total": 2005.014075595056, "count": 232521, "self": 1582.5125016419074, "children": { "SubprocessEnvManager._take_step": { "total": 419.6083816300131, "count": 232521, "self": 16.015653750885576, "children": { "TorchPolicy.evaluate": { "total": 403.59272787912755, "count": 222853, "self": 403.59272787912755 } } }, "workers": { "total": 2.8931923231355086, "count": 232521, "self": 0.0, "children": { "worker_root": { "total": 2522.9628815539368, "count": 232521, "is_parallel": true, "self": 1245.8318174879764, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009756629999628785, "count": 1, "is_parallel": true, "self": 0.0002780850002181978, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006975779997446807, "count": 2, "is_parallel": true, "self": 0.0006975779997446807 } } }, "UnityEnvironment.step": { "total": 0.02982915100005812, "count": 1, "is_parallel": true, "self": 0.00041200200030289125, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021066399995106622, "count": 1, "is_parallel": true, "self": 0.00021066399995106622 }, "communicator.exchange": { "total": 0.028377596999916932, "count": 1, "is_parallel": true, "self": 0.028377596999916932 }, "steps_from_proto": { "total": 0.0008288879998872289, "count": 1, "is_parallel": true, "self": 0.0002583019997928204, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005705860000944085, "count": 2, "is_parallel": true, "self": 0.0005705860000944085 } } } } } } }, "UnityEnvironment.step": { "total": 1277.1310640659603, "count": 232520, "is_parallel": true, "self": 38.969540610025206, "children": { "UnityEnvironment._generate_step_input": { "total": 85.56195112209912, "count": 232520, "is_parallel": true, "self": 85.56195112209912 }, "communicator.exchange": { "total": 1059.5881953820176, "count": 232520, "is_parallel": true, "self": 1059.5881953820176 }, "steps_from_proto": { "total": 93.01137695181842, "count": 232520, "is_parallel": true, "self": 35.357685396648776, "children": { "_process_rank_one_or_two_observation": { "total": 57.653691555169644, "count": 465040, "is_parallel": true, "self": 57.653691555169644 } } } } } } } } } } }, "trainer_advance": { "total": 513.174290801943, "count": 232521, "self": 6.65927943398151, "children": { "process_trajectory": { "total": 167.76942514596067, "count": 232521, "self": 166.3640643339611, "children": { "RLTrainer._checkpoint": { "total": 1.4053608119995715, "count": 10, "self": 1.4053608119995715 } } }, "_update_policy": { "total": 338.74558622200084, "count": 97, "self": 271.7071193299864, "children": { "TorchPPOOptimizer.update": { "total": 67.03846689201441, "count": 2910, "self": 67.03846689201441 } } } } } } }, "trainer_threads": { "total": 1.0090002433571499e-06, "count": 1, "self": 1.0090002433571499e-06 }, "TrainerController._save_models": { "total": 0.10927104200027316, "count": 1, "self": 0.0018335470003876253, "children": { "RLTrainer._checkpoint": { "total": 0.10743749499988553, "count": 1, "self": 0.10743749499988553 } } } } } } }