{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.1222777366638184, "min": 2.1222777366638184, "max": 2.8603274822235107, "count": 6 }, "SnowballTarget.Policy.Entropy.sum": { "value": 20520.302734375, "min": 20520.302734375, "max": 29324.078125, "count": 6 }, "SnowballTarget.Step.mean": { "value": 59976.0, "min": 9952.0, "max": 59976.0, "count": 6 }, "SnowballTarget.Step.sum": { "value": 59976.0, "min": 9952.0, "max": 59976.0, "count": 6 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 5.6423187255859375, "min": 0.24298718571662903, "max": 5.6423187255859375, "count": 6 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1156.67529296875, "min": 47.1395149230957, "max": 1156.67529296875, "count": 6 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 6 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 6 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0680542363539822, "min": 0.06448820029892136, "max": 0.07130624010711542, "count": 6 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.340271181769911, "min": 0.26738853977682686, "max": 0.35653120053557713, "count": 6 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.29524299665993337, "min": 0.10660545315876531, "max": 0.29524299665993337, "count": 6 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.4762149832996667, "min": 0.42642181263506124, "max": 1.4762149832996667, "count": 6 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.544009152e-05, "min": 2.544009152e-05, "max": 0.00027294000901999997, "count": 6 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0001272004576, "min": 0.0001272004576, "max": 0.0011172001276, "count": 6 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10848000000000002, "min": 0.10848000000000002, "max": 0.19098, "count": 6 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5424000000000001, "min": 0.49992000000000014, "max": 0.8724000000000001, "count": 6 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0004331519999999999, "min": 0.0004331519999999999, "max": 0.004549902, "count": 6 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0021657599999999996, "min": 0.0021657599999999996, "max": 0.01863276, "count": 6 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 13.909090909090908, "min": 3.090909090909091, "max": 13.909090909090908, "count": 6 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 765.0, "min": 136.0, "max": 765.0, "count": 6 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 13.909090909090908, "min": 3.090909090909091, "max": 13.909090909090908, "count": 6 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 765.0, "min": 136.0, "max": 765.0, "count": 6 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 6 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1725977065", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1725977247" }, "total": 182.0589623599999, "count": 1, "self": 0.5428975339998487, "children": { "run_training.setup": { "total": 0.0785293050000746, "count": 1, "self": 0.0785293050000746 }, "TrainerController.start_learning": { "total": 181.43753552099997, "count": 1, "self": 0.2878821229901405, "children": { "TrainerController._reset_env": { "total": 2.1628932000000987, "count": 1, "self": 2.1628932000000987 }, "TrainerController.advance": { "total": 178.89681454800962, "count": 5478, "self": 0.1314930490145798, "children": { "env_step": { "total": 178.76532149899504, "count": 5478, "self": 137.61047129000644, "children": { "SubprocessEnvManager._take_step": { "total": 41.02759959699688, "count": 5478, "self": 0.7611977679955544, "children": { "TorchPolicy.evaluate": { "total": 40.266401829001325, "count": 5478, "self": 40.266401829001325 } } }, "workers": { "total": 0.1272506119917125, "count": 5478, "self": 0.0, "children": { "worker_root": { "total": 180.78247003001684, "count": 5478, "is_parallel": true, "self": 85.64688459402373, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004937291000032928, "count": 1, "is_parallel": true, "self": 0.0016803930000151013, "children": { "_process_rank_one_or_two_observation": { "total": 0.003256898000017827, "count": 10, "is_parallel": true, "self": 0.003256898000017827 } } }, "UnityEnvironment.step": { "total": 0.08283363400005328, "count": 1, "is_parallel": true, "self": 0.0009711529999094637, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045539400002780894, "count": 1, "is_parallel": true, "self": 0.00045539400002780894 }, "communicator.exchange": { "total": 0.07698002400002224, "count": 1, "is_parallel": true, "self": 0.07698002400002224 }, "steps_from_proto": { "total": 0.004427063000093767, "count": 1, "is_parallel": true, "self": 0.0011134849999052676, "children": { "_process_rank_one_or_two_observation": { "total": 0.0033135780001884996, "count": 10, "is_parallel": true, "self": 0.0033135780001884996 } } } } } } }, "UnityEnvironment.step": { "total": 95.13558543599311, "count": 5477, "is_parallel": true, "self": 4.590552764978611, "children": { "UnityEnvironment._generate_step_input": { "total": 2.250011122001979, "count": 5477, "is_parallel": true, "self": 2.250011122001979 }, "communicator.exchange": { "total": 74.74543552700516, "count": 5477, "is_parallel": true, "self": 74.74543552700516 }, "steps_from_proto": { "total": 13.549586022007361, "count": 5477, "is_parallel": true, "self": 2.7187178270178265, "children": { "_process_rank_one_or_two_observation": { "total": 10.830868194989534, "count": 54770, "is_parallel": true, "self": 10.830868194989534 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00021429399998851295, "count": 1, "self": 0.00021429399998851295, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 176.7374168670642, "count": 229357, "is_parallel": true, "self": 5.540629778078483, "children": { "process_trajectory": { "total": 97.95098081398532, "count": 229357, "is_parallel": true, "self": 96.62720826198529, "children": { "RLTrainer._checkpoint": { "total": 1.3237725520000367, "count": 4, "is_parallel": true, "self": 1.3237725520000367 } } }, "_update_policy": { "total": 73.2458062750004, "count": 27, "is_parallel": true, "self": 21.031924708000815, "children": { "TorchPPOOptimizer.update": { "total": 52.21388156699959, "count": 1374, "is_parallel": true, "self": 52.21388156699959 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08973135600012938, "count": 1, "self": 0.0013072440001451469, "children": { "RLTrainer._checkpoint": { "total": 0.08842411199998423, "count": 1, "self": 0.08842411199998423 } } } } } } }