{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6862497329711914, "min": 0.6552515029907227, "max": 2.8428843021392822, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6582.50732421875, "min": 6347.6259765625, "max": 29020.1640625, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.695756912231445, "min": 0.3072643578052521, "max": 13.759556770324707, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2807.630126953125, "min": 59.60928726196289, "max": 2807.630126953125, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06382315461158607, "min": 0.06118524266796656, "max": 0.07484577231276918, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3191157730579303, "min": 0.24474097067186623, "max": 0.3728141247506488, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16815492767913667, "min": 0.13116641822453662, "max": 0.28046553023889953, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8407746383956833, "min": 0.5246656728981465, "max": 1.4023276511944975, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 3.0528989824000028e-06, "min": 3.0528989824000028e-06, "max": 0.00029675280108239997, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.5264494912000015e-05, "min": 1.5264494912000015e-05, "max": 0.001454064015312, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10101760000000001, "min": 0.10101760000000001, "max": 0.19891759999999997, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5050880000000001, "min": 0.41199040000000003, "max": 0.984688, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.0778240000000044e-05, "min": 6.0778240000000044e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003038912000000002, "min": 0.0003038912000000002, "max": 0.0242359312, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.581818181818182, "min": 3.4318181818181817, "max": 27.163636363636364, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1462.0, "min": 151.0, "max": 1494.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.581818181818182, "min": 3.4318181818181817, "max": 27.163636363636364, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1462.0, "min": 151.0, "max": 1494.0, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680006949", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1680007940" }, "total": 991.0241347240001, "count": 1, "self": 0.4331869140003164, "children": { "run_training.setup": { "total": 0.10909364299982371, "count": 1, "self": 0.10909364299982371 }, "TrainerController.start_learning": { "total": 990.4818541669999, "count": 1, "self": 0.838118010996368, "children": { "TrainerController._reset_env": { "total": 8.431820031999905, "count": 1, "self": 8.431820031999905 }, "TrainerController.advance": { "total": 981.0865343620037, "count": 45464, "self": 0.8882832679885269, "children": { "env_step": { "total": 693.3801975859685, "count": 45464, "self": 567.0031829649961, "children": { "SubprocessEnvManager._take_step": { "total": 125.84557056697508, "count": 45464, "self": 6.93332973902443, "children": { "TorchPolicy.evaluate": { "total": 118.91224082795065, "count": 45464, "self": 118.91224082795065 } } }, "workers": { "total": 0.5314440539973475, "count": 45464, "self": 0.0, "children": { "worker_root": { "total": 987.4322079959543, "count": 45464, "is_parallel": true, "self": 486.7480606049503, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0062808270001823985, "count": 1, "is_parallel": true, "self": 0.004719443999874784, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015613830003076146, "count": 10, "is_parallel": true, "self": 0.0015613830003076146 } } }, "UnityEnvironment.step": { "total": 0.03437766299998657, "count": 1, "is_parallel": true, "self": 0.0006794840003294667, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037672499979635177, "count": 1, "is_parallel": true, "self": 0.00037672499979635177 }, "communicator.exchange": { "total": 0.031576019999874916, "count": 1, "is_parallel": true, "self": 0.031576019999874916 }, "steps_from_proto": { "total": 0.0017454339999858348, "count": 1, "is_parallel": true, "self": 0.00035070000035375415, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013947339996320807, "count": 10, "is_parallel": true, "self": 0.0013947339996320807 } } } } } } }, "UnityEnvironment.step": { "total": 500.684147391004, "count": 45463, "is_parallel": true, "self": 23.50415237105085, "children": { "UnityEnvironment._generate_step_input": { "total": 12.620105701034618, "count": 45463, "is_parallel": true, "self": 12.620105701034618 }, "communicator.exchange": { "total": 390.96815782094427, "count": 45463, "is_parallel": true, "self": 390.96815782094427 }, "steps_from_proto": { "total": 73.59173149797425, "count": 45463, "is_parallel": true, "self": 13.862445530092373, "children": { "_process_rank_one_or_two_observation": { "total": 59.72928596788188, "count": 454630, "is_parallel": true, "self": 59.72928596788188 } } } } } } } } } } }, "trainer_advance": { "total": 286.81805350804666, "count": 45464, "self": 1.0192455620783676, "children": { "process_trajectory": { "total": 59.971309867966056, "count": 45464, "self": 58.45250307496599, "children": { "RLTrainer._checkpoint": { "total": 1.518806793000067, "count": 10, "self": 1.518806793000067 } } }, "_update_policy": { "total": 225.82749807800224, "count": 227, "self": 119.3114454989909, "children": { "TorchPPOOptimizer.update": { "total": 106.51605257901133, "count": 11574, "self": 106.51605257901133 } } } } } } }, "trainer_threads": { "total": 8.849997357174288e-07, "count": 1, "self": 8.849997357174288e-07 }, "TrainerController._save_models": { "total": 0.12538087700022515, "count": 1, "self": 0.0009051020001606958, "children": { "RLTrainer._checkpoint": { "total": 0.12447577500006446, "count": 1, "self": 0.12447577500006446 } } } } } } }