{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9815138578414917, "min": 0.9815138578414917, "max": 1.1821503639221191, "count": 8 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9468.6640625, "min": 6891.9365234375, "max": 11955.521484375, "count": 8 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 129968.0, "max": 199984.0, "count": 8 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 129968.0, "max": 199984.0, "count": 8 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.673952102661133, "min": 11.362044334411621, "max": 12.673952102661133, "count": 8 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2598.16015625, "min": 1170.29052734375, "max": 2598.16015625, "count": 8 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 8 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 4378.0, "max": 10945.0, "count": 8 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07086437849451185, "min": 0.06403256360360554, "max": 0.07574787820176068, "count": 8 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3543218924725593, "min": 0.13303252805096288, "max": 0.36832285885854316, "count": 8 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2181383147543552, "min": 0.1968190373451102, "max": 0.24291060601963715, "count": 8 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.090691573771776, "min": 0.41379601263678545, "max": 1.106732099371798, "count": 8 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.620097459999994e-06, "min": 7.620097459999994e-06, "max": 0.00010827006390999999, "count": 8 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.810048729999997e-05, "min": 3.810048729999997e-05, "max": 0.00048360033879999993, "count": 8 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10254, "min": 0.10254, "max": 0.13609, "count": 8 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5127, "min": 0.27218, "max": 0.6612000000000001, "count": 8 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001367459999999999, "min": 0.0001367459999999999, "max": 0.0018108909999999998, "count": 8 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0006837299999999995, "min": 0.0006837299999999995, "max": 0.008093880000000003, "count": 8 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.78181818181818, "min": 24.09090909090909, "max": 25.25, "count": 8 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1363.0, "min": 530.0, "max": 1366.0, "count": 8 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.78181818181818, "min": 24.09090909090909, "max": 25.25, "count": 8 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1363.0, "min": 530.0, "max": 1366.0, "count": 8 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 8 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 8 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677248488", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677248664" }, "total": 176.48783581099997, "count": 1, "self": 0.7908957929998905, "children": { "run_training.setup": { "total": 0.11163163900005202, "count": 1, "self": 0.11163163900005202 }, "TrainerController.start_learning": { "total": 175.58530837900003, "count": 1, "self": 0.2128481919951355, "children": { "TrainerController._reset_env": { "total": 6.083875421000016, "count": 1, "self": 6.083875421000016 }, "TrainerController.advance": { "total": 169.11183770500486, "count": 6877, "self": 0.10986581899987868, "children": { "env_step": { "total": 169.00197188600498, "count": 6877, "self": 115.69572960101004, "children": { "SubprocessEnvManager._take_step": { "total": 53.203091808996305, "count": 6877, "self": 0.5449916209936418, "children": { "TorchPolicy.evaluate": { "total": 52.65810018800266, "count": 6877, "self": 11.12593075599682, "children": { "TorchPolicy.sample_actions": { "total": 41.532169432005844, "count": 6877, "self": 41.532169432005844 } } } } }, "workers": { "total": 0.10315047599863192, "count": 6877, "self": 0.0, "children": { "worker_root": { "total": 174.99380368200343, "count": 6877, "is_parallel": true, "self": 86.3441401180014, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005599716000006083, "count": 1, "is_parallel": true, "self": 0.0023935140000048705, "children": { "_process_rank_one_or_two_observation": { "total": 0.0032062020000012126, "count": 10, "is_parallel": true, "self": 0.0032062020000012126 } } }, "UnityEnvironment.step": { "total": 0.034815048000041315, "count": 1, "is_parallel": true, "self": 0.0005669120000675321, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00035793299991837557, "count": 1, "is_parallel": true, "self": 0.00035793299991837557 }, "communicator.exchange": { "total": 0.03188507400000162, "count": 1, "is_parallel": true, "self": 0.03188507400000162 }, "steps_from_proto": { "total": 0.0020051290000537847, "count": 1, "is_parallel": true, "self": 0.00048629800016897207, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015188309998848126, "count": 10, "is_parallel": true, "self": 0.0015188309998848126 } } } } } } }, "UnityEnvironment.step": { "total": 88.64966356400203, "count": 6876, "is_parallel": true, "self": 3.5055579360082447, "children": { "UnityEnvironment._generate_step_input": { "total": 1.9486607639973954, "count": 6876, "is_parallel": true, "self": 1.9486607639973954 }, "communicator.exchange": { "total": 71.4519814719996, "count": 6876, "is_parallel": true, "self": 71.4519814719996 }, "steps_from_proto": { "total": 11.743463391996784, "count": 6876, "is_parallel": true, "self": 2.543664004005336, "children": { "_process_rank_one_or_two_observation": { "total": 9.199799387991447, "count": 68760, "is_parallel": true, "self": 9.199799387991447 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014593799994599976, "count": 1, "self": 0.00014593799994599976, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 167.8312638539826, "count": 153086, "is_parallel": true, "self": 3.847226824004906, "children": { "process_trajectory": { "total": 95.52795781597752, "count": 153086, "is_parallel": true, "self": 95.13844745997756, "children": { "RLTrainer._checkpoint": { "total": 0.38951035599995976, "count": 2, "is_parallel": true, "self": 0.38951035599995976 } } }, "_update_policy": { "total": 68.45607921400017, "count": 34, "is_parallel": true, "self": 23.5676672550004, "children": { "TorchPPOOptimizer.update": { "total": 44.88841195899977, "count": 1731, "is_parallel": true, "self": 44.88841195899977 } } } } } } } } }, "TrainerController._save_models": { "total": 0.17660112300006858, "count": 1, "self": 0.0019351140000480882, "children": { "RLTrainer._checkpoint": { "total": 0.1746660090000205, "count": 1, "self": 0.1746660090000205 } } } } } } }