{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.7666914463043213, "min": 1.7666914463043213, "max": 2.864610433578491, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 18150.98828125, "min": 16997.880859375, "max": 29336.4765625, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 8.373676300048828, "min": 0.2591015696525574, "max": 8.373676300048828, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 1708.22998046875, "min": 50.26570510864258, "max": 1708.22998046875, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06782104940080613, "min": 0.06306661487221443, "max": 0.07333418765078487, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.33910524700403066, "min": 0.25226645948885773, "max": 0.36667093825392433, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24595451080331615, "min": 0.11039579009030051, "max": 0.273880765134213, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.2297725540165807, "min": 0.44158316036120204, "max": 1.3021115797991847, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.6464094511999996e-05, "min": 1.6464094511999996e-05, "max": 0.000283764005412, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.232047255999999e-05, "min": 8.232047255999999e-05, "max": 0.00127032007656, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.105488, "min": 0.105488, "max": 0.194588, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.52744, "min": 0.4615520000000001, "max": 0.92344, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0002838512, "min": 0.0002838512, "max": 0.0047299412, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001419256, "min": 0.001419256, "max": 0.021179656, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 17.618181818181817, "min": 3.409090909090909, "max": 17.65909090909091, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 969.0, "min": 150.0, "max": 969.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 17.618181818181817, "min": 3.409090909090909, "max": 17.65909090909091, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 969.0, "min": 150.0, "max": 969.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1705237979", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1705238263" }, "total": 284.202546646, "count": 1, "self": 0.48592113600011544, "children": { "run_training.setup": { "total": 0.06625769900006162, "count": 1, "self": 0.06625769900006162 }, "TrainerController.start_learning": { "total": 283.6503678109998, "count": 1, "self": 0.4266442560035557, "children": { "TrainerController._reset_env": { "total": 3.508615751999969, "count": 1, "self": 3.508615751999969 }, "TrainerController.advance": { "total": 279.6055831969961, "count": 9133, "self": 0.194785510984957, "children": { "env_step": { "total": 279.41079768601116, "count": 9133, "self": 186.41531429699876, "children": { "SubprocessEnvManager._take_step": { "total": 92.80318400000215, "count": 9133, "self": 0.9434330710164431, "children": { "TorchPolicy.evaluate": { "total": 91.8597509289857, "count": 9133, "self": 91.8597509289857 } } }, "workers": { "total": 0.1922993890102589, "count": 9133, "self": 0.0, "children": { "worker_root": { "total": 282.6628585010085, "count": 9133, "is_parallel": true, "self": 136.93231525700185, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00600445000009131, "count": 1, "is_parallel": true, "self": 0.004456857000377568, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015475929997137428, "count": 10, "is_parallel": true, "self": 0.0015475929997137428 } } }, "UnityEnvironment.step": { "total": 0.04370939099999305, "count": 1, "is_parallel": true, "self": 0.0006702860000586952, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00047198399988701567, "count": 1, "is_parallel": true, "self": 0.00047198399988701567 }, "communicator.exchange": { "total": 0.04027892399994926, "count": 1, "is_parallel": true, "self": 0.04027892399994926 }, "steps_from_proto": { "total": 0.00228819700009808, "count": 1, "is_parallel": true, "self": 0.0004627359999176406, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018254610001804394, "count": 10, "is_parallel": true, "self": 0.0018254610001804394 } } } } } } }, "UnityEnvironment.step": { "total": 145.73054324400664, "count": 9132, "is_parallel": true, "self": 6.525278903001663, "children": { "UnityEnvironment._generate_step_input": { "total": 3.42183450600146, "count": 9132, "is_parallel": true, "self": 3.42183450600146 }, "communicator.exchange": { "total": 114.04990232000341, "count": 9132, "is_parallel": true, "self": 114.04990232000341 }, "steps_from_proto": { "total": 21.733527515000105, "count": 9132, "is_parallel": true, "self": 4.144910251000738, "children": { "_process_rank_one_or_two_observation": { "total": 17.588617263999367, "count": 91320, "is_parallel": true, "self": 17.588617263999367 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0004665500000555767, "count": 1, "self": 0.0004665500000555767, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 275.9207142779683, "count": 413959, "is_parallel": true, "self": 9.385631704065872, "children": { "process_trajectory": { "total": 153.61151503890142, "count": 413959, "is_parallel": true, "self": 153.31683383490144, "children": { "RLTrainer._checkpoint": { "total": 0.29468120399997133, "count": 2, "is_parallel": true, "self": 0.29468120399997133 } } }, "_update_policy": { "total": 112.92356753500098, "count": 45, "is_parallel": true, "self": 35.549154577004856, "children": { "TorchPPOOptimizer.update": { "total": 77.37441295799613, "count": 2292, "is_parallel": true, "self": 77.37441295799613 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10905805600009444, "count": 1, "self": 0.0012185160001081385, "children": { "RLTrainer._checkpoint": { "total": 0.1078395399999863, "count": 1, "self": 0.1078395399999863 } } } } } } }