{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.2574926614761353, "min": 1.2574448585510254, "max": 1.418084740638733, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 62713.671875, "min": 61818.4453125, "max": 76607.7734375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 95.83783783783784, "min": 77.49607535321822, "max": 385.4923076923077, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49644.0, "min": 48783.0, "max": 50114.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999463.0, "min": 49884.0, "max": 1999463.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999463.0, "min": 49884.0, "max": 1999463.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.385010242462158, "min": 0.19122472405433655, "max": 2.468559741973877, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1235.435302734375, "min": 24.66798973083496, "max": 1556.260986328125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7006998300322236, "min": 1.8974484681159027, "max": 4.101620939816776, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1916.9625119566917, "min": 244.77085238695145, "max": 2534.1661923527718, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7006998300322236, "min": 1.8974484681159027, "max": 4.101620939816776, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1916.9625119566917, "min": 244.77085238695145, "max": 2534.1661923527718, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.019341733674082207, "min": 0.014545311936672078, "max": 0.01944458357029362, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05802520102224662, "min": 0.029090623873344157, "max": 0.05802520102224662, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.069497550620387, "min": 0.04631982874125242, "max": 0.08275427911430597, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.208492651861161, "min": 0.09263965748250484, "max": 0.2207494791597128, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 5.8140155038833255e-06, "min": 5.8140155038833255e-06, "max": 0.000492284376543125, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.7442046511649977e-05, "min": 1.7442046511649977e-05, "max": 0.0014068427686314499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10232556666666666, "min": 0.10232556666666666, "max": 0.29691375, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3069767, "min": 0.2149223, "max": 0.8627370999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.802288833333326e-05, "min": 6.802288833333326e-05, "max": 0.0049229980625, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002040686649999998, "min": 0.0002040686649999998, "max": 0.014070290645, "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": "1765177782", "python_version": "3.10.12 (main, Nov 4 2025, 08:48:33) [GCC 11.4.0]", "command_line_arguments": "/home/harinarayannan/.local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy-screen-big --force --env-args -screen-width 1920 -screen-height 1080 -window-mode 1", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu117", "numpy_version": "1.23.5", "end_time_seconds": "1765178781" }, "total": 998.2744856110075, "count": 1, "self": 0.2173715609824285, "children": { "run_training.setup": { "total": 0.019625255023129284, "count": 1, "self": 0.019625255023129284 }, "TrainerController.start_learning": { "total": 998.037488795002, "count": 1, "self": 2.4545747421798296, "children": { "TrainerController._reset_env": { "total": 3.8174973640125245, "count": 1, "self": 3.8174973640125245 }, "TrainerController.advance": { "total": 991.7110319837811, "count": 232912, "self": 2.2082955152727664, "children": { "env_step": { "total": 734.6443906969507, "count": 232912, "self": 564.4819226957625, "children": { "SubprocessEnvManager._take_step": { "total": 168.62374972127145, "count": 232912, "self": 8.928723814606201, "children": { "TorchPolicy.evaluate": { "total": 159.69502590666525, "count": 223034, "self": 159.69502590666525 } } }, "workers": { "total": 1.538718279916793, "count": 232912, "self": 0.0, "children": { "worker_root": { "total": 995.1427736839396, "count": 232912, "is_parallel": true, "self": 557.0301751194056, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000401530007366091, "count": 1, "is_parallel": true, "self": 9.10409726202488e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003104890347458422, "count": 2, "is_parallel": true, "self": 0.0003104890347458422 } } }, "UnityEnvironment.step": { "total": 0.010468287975527346, "count": 1, "is_parallel": true, "self": 0.00014585396274924278, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00010539998766034842, "count": 1, "is_parallel": true, "self": 0.00010539998766034842 }, "communicator.exchange": { "total": 0.009965075005311519, "count": 1, "is_parallel": true, "self": 0.009965075005311519 }, "steps_from_proto": { "total": 0.00025195901980623603, "count": 1, "is_parallel": true, "self": 7.11640459485352e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.00018079497385770082, "count": 2, "is_parallel": true, "self": 0.00018079497385770082 } } } } } } }, "UnityEnvironment.step": { "total": 438.112598564534, "count": 232911, "is_parallel": true, "self": 13.241522364900447, "children": { "UnityEnvironment._generate_step_input": { "total": 21.39470614126185, "count": 232911, "is_parallel": true, "self": 21.39470614126185 }, "communicator.exchange": { "total": 373.12126241630176, "count": 232911, "is_parallel": true, "self": 373.12126241630176 }, "steps_from_proto": { "total": 30.355107642069925, "count": 232911, "is_parallel": true, "self": 9.923103735316545, "children": { "_process_rank_one_or_two_observation": { "total": 20.43200390675338, "count": 465822, "is_parallel": true, "self": 20.43200390675338 } } } } } } } } } } }, "trainer_advance": { "total": 254.85834577155765, "count": 232912, "self": 3.8937603514641523, "children": { "process_trajectory": { "total": 72.06531172979157, "count": 232912, "self": 71.5339818628272, "children": { "RLTrainer._checkpoint": { "total": 0.53132986696437, "count": 10, "self": 0.53132986696437 } } }, "_update_policy": { "total": 178.89927369030192, "count": 97, "self": 137.7613807701273, "children": { "TorchPPOOptimizer.update": { "total": 41.137892920174636, "count": 3880, "self": 41.137892920174636 } } } } } } }, "trainer_threads": { "total": 6.540212780237198e-07, "count": 1, "self": 6.540212780237198e-07 }, "TrainerController._save_models": { "total": 0.05438405100721866, "count": 1, "self": 0.0014761859783902764, "children": { "RLTrainer._checkpoint": { "total": 0.05290786502882838, "count": 1, "self": 0.05290786502882838 } } } } } } }