{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4116276502609253, "min": 1.4116276502609253, "max": 1.4261356592178345, "count": 17 }, "Huggy.Policy.Entropy.sum": { "value": 69762.640625, "min": 68072.4375, "max": 75953.6875, "count": 17 }, "Huggy.Environment.EpisodeLength.mean": { "value": 95.56370656370656, "min": 86.78734622144113, "max": 390.328125, "count": 17 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49502.0, "min": 48925.0, "max": 50442.0, "count": 17 }, "Huggy.Step.mean": { "value": 849930.0, "min": 49782.0, "max": 849930.0, "count": 17 }, "Huggy.Step.sum": { "value": 849930.0, "min": 49782.0, "max": 849930.0, "count": 17 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.347731590270996, "min": 0.058761898428201675, "max": 2.347731590270996, "count": 17 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1216.125, "min": 7.462760925292969, "max": 1326.5009765625, "count": 17 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.804619862191005, "min": 1.785732222823646, "max": 4.017569181960743, "count": 17 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1970.7930886149406, "min": 226.78799229860306, "max": 2216.7429639697075, "count": 17 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.804619862191005, "min": 1.785732222823646, "max": 4.017569181960743, "count": 17 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1970.7930886149406, "min": 226.78799229860306, "max": 2216.7429639697075, "count": 17 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014863286877759188, "min": 0.014228061723406425, "max": 0.019232102753812798, "count": 17 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.044589860633277564, "min": 0.02845612344681285, "max": 0.055172760633710516, "count": 17 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.049697367184691955, "min": 0.022404397682597242, "max": 0.05966483770559232, "count": 17 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14909210155407587, "min": 0.044808795365194484, "max": 0.1593497068931659, "count": 17 }, "Huggy.Policy.LearningRate.mean": { "value": 0.00017645164118280002, "min": 0.00017645164118280002, "max": 0.00029528055157315003, "count": 17 }, "Huggy.Policy.LearningRate.sum": { "value": 0.0005293549235484001, "min": 0.00036833332722224993, "max": 0.0008439345186884997, "count": 17 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1588172, "min": 0.1588172, "max": 0.19842685000000004, "count": 17 }, "Huggy.Policy.Epsilon.sum": { "value": 0.4764516, "min": 0.32277775000000003, "max": 0.5813115, "count": 17 }, "Huggy.Policy.Beta.mean": { "value": 0.00294497828, "min": 0.00294497828, "max": 0.004921499814999999, "count": 17 }, "Huggy.Policy.Beta.sum": { "value": 0.008834934840000001, "min": 0.006146609724999998, "max": 0.01406744385, "count": 17 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 17 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1740503207", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1740504295" }, "total": 1087.7918451189998, "count": 1, "self": 0.25631425199981095, "children": { "run_training.setup": { "total": 0.029493561999970552, "count": 1, "self": 0.029493561999970552 }, "TrainerController.start_learning": { "total": 1087.506037305, "count": 1, "self": 1.9912854800254536, "children": { "TrainerController._reset_env": { "total": 3.4235518460000094, "count": 1, "self": 3.4235518460000094 }, "TrainerController.advance": { "total": 1081.9096431219746, "count": 99722, "self": 2.147565727984329, "children": { "env_step": { "total": 873.4021913800009, "count": 99722, "self": 683.9261875319992, "children": { "SubprocessEnvManager._take_step": { "total": 188.27272667101806, "count": 99722, "self": 7.147975727968969, "children": { "TorchPolicy.evaluate": { "total": 181.1247509430491, "count": 96395, "self": 181.1247509430491 } } }, "workers": { "total": 1.2032771769836472, "count": 99722, "self": 0.0, "children": { "worker_root": { "total": 1081.6883857630282, "count": 99722, "is_parallel": true, "self": 524.5143495760567, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012097999999696185, "count": 1, "is_parallel": true, "self": 0.0004850019998912103, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007247980000784082, "count": 2, "is_parallel": true, "self": 0.0007247980000784082 } } }, "UnityEnvironment.step": { "total": 0.031611483000006046, "count": 1, "is_parallel": true, "self": 0.00030980999997609615, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001872310000408106, "count": 1, "is_parallel": true, "self": 0.0001872310000408106 }, "communicator.exchange": { "total": 0.030393828000001122, "count": 1, "is_parallel": true, "self": 0.030393828000001122 }, "steps_from_proto": { "total": 0.0007206139999880179, "count": 1, "is_parallel": true, "self": 0.00020344499989732867, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005171690000906892, "count": 2, "is_parallel": true, "self": 0.0005171690000906892 } } } } } } }, "UnityEnvironment.step": { "total": 557.1740361869715, "count": 99721, "is_parallel": true, "self": 16.578050828935147, "children": { "UnityEnvironment._generate_step_input": { "total": 36.61730686103067, "count": 99721, "is_parallel": true, "self": 36.61730686103067 }, "communicator.exchange": { "total": 464.44547773801094, "count": 99721, "is_parallel": true, "self": 464.44547773801094 }, "steps_from_proto": { "total": 39.53320075899478, "count": 99721, "is_parallel": true, "self": 14.61423453502789, "children": { "_process_rank_one_or_two_observation": { "total": 24.91896622396689, "count": 199442, "is_parallel": true, "self": 24.91896622396689 } } } } } } } } } } }, "trainer_advance": { "total": 206.35988601398924, "count": 99722, "self": 2.871565190997444, "children": { "process_trajectory": { "total": 67.65410750599278, "count": 99722, "self": 66.99601412899244, "children": { "RLTrainer._checkpoint": { "total": 0.6580933770003412, "count": 4, "self": 0.6580933770003412 } } }, "_update_policy": { "total": 135.834213316999, "count": 42, "self": 108.13215333499727, "children": { "TorchPPOOptimizer.update": { "total": 27.702059982001742, "count": 1250, "self": 27.702059982001742 } } } } } } }, "trainer_threads": { "total": 1.7459999526181491e-06, "count": 1, "self": 1.7459999526181491e-06 }, "TrainerController._save_models": { "total": 0.1815551110000797, "count": 1, "self": 0.002802935000090656, "children": { "RLTrainer._checkpoint": { "total": 0.17875217599998905, "count": 1, "self": 0.17875217599998905 } } } } } } }