{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7894349694252014, "min": 0.7894349694252014, "max": 2.848572015762329, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7572.26025390625, "min": 7572.26025390625, "max": 29234.89453125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.699254035949707, "min": 0.3859694302082062, "max": 12.699254035949707, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2476.3544921875, "min": 74.87806701660156, "max": 2575.423828125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06831628586309414, "min": 0.062446750758767045, "max": 0.07389995663577471, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27326514345237657, "min": 0.2602254519492728, "max": 0.3656835710383294, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21551618841933268, "min": 0.11361452613560044, "max": 0.2750495168508268, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8620647536773307, "min": 0.45445810454240176, "max": 1.3752475842541338, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.227272727272727, "min": 3.022727272727273, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1110.0, "min": 133.0, "max": 1390.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.227272727272727, "min": 3.022727272727273, "max": 25.272727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1110.0, "min": 133.0, "max": 1390.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693537848", "python_version": "3.9.7 (default, Sep 16 2021, 13:09:58) \n[GCC 7.5.0]", "command_line_arguments": "/home/jiangchun/anaconda3/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.10.1+cu111", "numpy_version": "1.21.2", "end_time_seconds": "1693538268" }, "total": 420.55999274970964, "count": 1, "self": 0.26966539351269603, "children": { "run_training.setup": { "total": 0.03747469000518322, "count": 1, "self": 0.03747469000518322 }, "TrainerController.start_learning": { "total": 420.25285266619176, "count": 1, "self": 0.44111799681559205, "children": { "TrainerController._reset_env": { "total": 2.806502046994865, "count": 1, "self": 2.806502046994865 }, "TrainerController.advance": { "total": 416.89016689080745, "count": 18207, "self": 0.1766283200122416, "children": { "env_step": { "total": 416.7135385707952, "count": 18207, "self": 238.02699806075543, "children": { "SubprocessEnvManager._take_step": { "total": 178.5052353576757, "count": 18207, "self": 1.1663948660716414, "children": { "TorchPolicy.evaluate": { "total": 177.33884049160406, "count": 18207, "self": 177.33884049160406 } } }, "workers": { "total": 0.18130515236407518, "count": 18207, "self": 0.0, "children": { "worker_root": { "total": 419.6346041560173, "count": 18207, "is_parallel": true, "self": 253.94948424678296, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0013728137128055096, "count": 1, "is_parallel": true, "self": 0.0003831889480352402, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009896247647702694, "count": 10, "is_parallel": true, "self": 0.0009896247647702694 } } }, "UnityEnvironment.step": { "total": 0.031236899085342884, "count": 1, "is_parallel": true, "self": 0.0002848492003977299, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002853190526366234, "count": 1, "is_parallel": true, "self": 0.0002853190526366234 }, "communicator.exchange": { "total": 0.029691906180232763, "count": 1, "is_parallel": true, "self": 0.029691906180232763 }, "steps_from_proto": { "total": 0.0009748246520757675, "count": 1, "is_parallel": true, "self": 0.0002200375311076641, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007547871209681034, "count": 10, "is_parallel": true, "self": 0.0007547871209681034 } } } } } } }, "UnityEnvironment.step": { "total": 165.68511990923434, "count": 18206, "is_parallel": true, "self": 5.178183088079095, "children": { "UnityEnvironment._generate_step_input": { "total": 2.990071809850633, "count": 18206, "is_parallel": true, "self": 2.990071809850633 }, "communicator.exchange": { "total": 141.024031967856, "count": 18206, "is_parallel": true, "self": 141.024031967856 }, "steps_from_proto": { "total": 16.492833043448627, "count": 18206, "is_parallel": true, "self": 3.208974115550518, "children": { "_process_rank_one_or_two_observation": { "total": 13.283858927898109, "count": 182060, "is_parallel": true, "self": 13.283858927898109 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00046836771070957184, "count": 1, "self": 0.00046836771070957184, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 415.1853808579035, "count": 524647, "is_parallel": true, "self": 5.44804802024737, "children": { "process_trajectory": { "total": 228.57862921757624, "count": 524647, "is_parallel": true, "self": 227.6980458344333, "children": { "RLTrainer._checkpoint": { "total": 0.8805833831429482, "count": 4, "is_parallel": true, "self": 0.8805833831429482 } } }, "_update_policy": { "total": 181.1587036200799, "count": 90, "is_parallel": true, "self": 34.584700054489076, "children": { "TorchPPOOptimizer.update": { "total": 146.57400356559083, "count": 4587, "is_parallel": true, "self": 146.57400356559083 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11459736386314034, "count": 1, "self": 0.0006024381145834923, "children": { "RLTrainer._checkpoint": { "total": 0.11399492574855685, "count": 1, "self": 0.11399492574855685 } } } } } } }