{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.280211925506592, "min": 2.280211925506592, "max": 2.8695173263549805, "count": 5 }, "SnowballTarget.Policy.Entropy.sum": { "value": 23100.826171875, "min": 23100.826171875, "max": 29386.7265625, "count": 5 }, "SnowballTarget.Step.mean": { "value": 49936.0, "min": 9952.0, "max": 49936.0, "count": 5 }, "SnowballTarget.Step.sum": { "value": 49936.0, "min": 9952.0, "max": 49936.0, "count": 5 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 4.3855977058410645, "min": 0.29490068554878235, "max": 4.3855977058410645, "count": 5 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 850.8059692382812, "min": 57.210731506347656, "max": 850.8059692382812, "count": 5 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 5 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 5 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07019796329561857, "min": 0.06794666571579143, "max": 0.07504163294957548, "count": 5 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2807918531824743, "min": 0.2807918531824743, "max": 0.37520816474787744, "count": 5 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2535587658046507, "min": 0.13059806538170532, "max": 0.27757449132554673, "count": 5 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.0142350632186028, "min": 0.5223922615268213, "max": 1.3878724566277336, "count": 5 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.9928090024000003e-05, "min": 2.9928090024000003e-05, "max": 0.00026752801082399996, "count": 5 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.00011971236009600001, "min": 0.00011971236009600001, "max": 0.0010701120432959998, "count": 5 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10997600000000002, "min": 0.10997600000000002, "max": 0.18917599999999998, "count": 5 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.4399040000000001, "min": 0.4399040000000001, "max": 0.8468800000000001, "count": 5 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0005078024, "min": 0.0005078024, "max": 0.0044598824, "count": 5 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0020312096, "min": 0.0020312096, "max": 0.0178395296, "count": 5 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 10.727272727272727, "min": 3.6136363636363638, "max": 10.727272727272727, "count": 5 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 472.0, "min": 159.0, "max": 530.0, "count": 5 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 10.727272727272727, "min": 3.6136363636363638, "max": 10.727272727272727, "count": 5 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 472.0, "min": 159.0, "max": 530.0, "count": 5 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1697175782", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697175899" }, "total": 116.74728019699978, "count": 1, "self": 0.6674990580004305, "children": { "run_training.setup": { "total": 0.043808397999782756, "count": 1, "self": 0.043808397999782756 }, "TrainerController.start_learning": { "total": 116.03597274099957, "count": 1, "self": 0.25001357100154564, "children": { "TrainerController._reset_env": { "total": 3.099544283999421, "count": 1, "self": 3.099544283999421 }, "TrainerController.advance": { "total": 112.51787465599864, "count": 4615, "self": 0.06529620703531691, "children": { "env_step": { "total": 112.45257844896332, "count": 4615, "self": 76.34982492590643, "children": { "SubprocessEnvManager._take_step": { "total": 36.034070072023496, "count": 4615, "self": 0.3543345810558094, "children": { "TorchPolicy.evaluate": { "total": 35.67973549096769, "count": 4615, "self": 35.67973549096769 } } }, "workers": { "total": 0.0686834510333938, "count": 4615, "self": 0.0, "children": { "worker_root": { "total": 115.4792870129886, "count": 4615, "is_parallel": true, "self": 56.51930467899365, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019277409992355388, "count": 1, "is_parallel": true, "self": 0.0006094230002418044, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013183179989937344, "count": 10, "is_parallel": true, "self": 0.0013183179989937344 } } }, "UnityEnvironment.step": { "total": 0.06010489999971469, "count": 1, "is_parallel": true, "self": 0.0006052499993529636, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00044186099967191694, "count": 1, "is_parallel": true, "self": 0.00044186099967191694 }, "communicator.exchange": { "total": 0.05716692200076068, "count": 1, "is_parallel": true, "self": 0.05716692200076068 }, "steps_from_proto": { "total": 0.0018908669999291305, "count": 1, "is_parallel": true, "self": 0.00038344000131473877, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015074269986143918, "count": 10, "is_parallel": true, "self": 0.0015074269986143918 } } } } } } }, "UnityEnvironment.step": { "total": 58.95998233399496, "count": 4614, "is_parallel": true, "self": 2.6201081659855845, "children": { "UnityEnvironment._generate_step_input": { "total": 1.3223246310026298, "count": 4614, "is_parallel": true, "self": 1.3223246310026298 }, "communicator.exchange": { "total": 46.73223755700201, "count": 4614, "is_parallel": true, "self": 46.73223755700201 }, "steps_from_proto": { "total": 8.285311980004735, "count": 4614, "is_parallel": true, "self": 1.5265699039109677, "children": { "_process_rank_one_or_two_observation": { "total": 6.7587420760937675, "count": 46140, "is_parallel": true, "self": 6.7587420760937675 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0006265689999054302, "count": 1, "self": 0.0006265689999054302, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 111.66931204606772, "count": 120338, "is_parallel": true, "self": 2.5173981640355123, "children": { "process_trajectory": { "total": 64.67400288903173, "count": 120338, "is_parallel": true, "self": 64.10358650003218, "children": { "RLTrainer._checkpoint": { "total": 0.570416388999547, "count": 1, "is_parallel": true, "self": 0.570416388999547 } } }, "_update_policy": { "total": 44.47791099300048, "count": 22, "is_parallel": true, "self": 13.703000551014156, "children": { "TorchPPOOptimizer.update": { "total": 30.77491044198632, "count": 1119, "is_parallel": true, "self": 30.77491044198632 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1679136610000569, "count": 1, "self": 0.0011775449993365328, "children": { "RLTrainer._checkpoint": { "total": 0.16673611600072036, "count": 1, "self": 0.16673611600072036 } } } } } } }