{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0191267728805542, "min": 1.0191267728805542, "max": 2.8414883613586426, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9685.78125, "min": 9685.78125, "max": 29005.9140625, "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": 11.250739097595215, "min": 0.41937342286109924, "max": 11.250739097595215, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2193.89404296875, "min": 81.35844421386719, "max": 2268.041015625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06686744179815457, "min": 0.06312745971095579, "max": 0.07259353222172792, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2674697671926183, "min": 0.25250983884382316, "max": 0.3629676611086396, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21205806177036435, "min": 0.1375554182324741, "max": 0.269474175806139, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8482322470814574, "min": 0.5502216729298964, "max": 1.347370879030695, "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.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 21.65909090909091, "min": 3.590909090909091, "max": 22.581818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 953.0, "min": 158.0, "max": 1242.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 21.65909090909091, "min": 3.590909090909091, "max": 22.581818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 953.0, "min": 158.0, "max": 1242.0, "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": "1764163597", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1764164037" }, "total": 439.513554064, "count": 1, "self": 0.4369494779998604, "children": { "run_training.setup": { "total": 0.026647394000065106, "count": 1, "self": 0.026647394000065106 }, "TrainerController.start_learning": { "total": 439.0499571920001, "count": 1, "self": 0.36314072699860844, "children": { "TrainerController._reset_env": { "total": 2.791192385000045, "count": 1, "self": 2.791192385000045 }, "TrainerController.advance": { "total": 435.8143913080015, "count": 18192, "self": 0.37141925300556977, "children": { "env_step": { "total": 316.4431244839965, "count": 18192, "self": 247.27249040199865, "children": { "SubprocessEnvManager._take_step": { "total": 68.95599511400178, "count": 18192, "self": 1.2339094640042276, "children": { "TorchPolicy.evaluate": { "total": 67.72208564999755, "count": 18192, "self": 67.72208564999755 } } }, "workers": { "total": 0.2146389679960521, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 437.2910299639957, "count": 18192, "is_parallel": true, "self": 219.99269793799192, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0049954900000557245, "count": 1, "is_parallel": true, "self": 0.003593891000491567, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014015989995641576, "count": 10, "is_parallel": true, "self": 0.0014015989995641576 } } }, "UnityEnvironment.step": { "total": 0.035222918000044956, "count": 1, "is_parallel": true, "self": 0.0005940110000892673, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003991150000501875, "count": 1, "is_parallel": true, "self": 0.0003991150000501875 }, "communicator.exchange": { "total": 0.032438654999964456, "count": 1, "is_parallel": true, "self": 0.032438654999964456 }, "steps_from_proto": { "total": 0.0017911369999410454, "count": 1, "is_parallel": true, "self": 0.0003532740000764534, "children": { "_process_rank_one_or_two_observation": { "total": 0.001437862999864592, "count": 10, "is_parallel": true, "self": 0.001437862999864592 } } } } } } }, "UnityEnvironment.step": { "total": 217.29833202600378, "count": 18191, "is_parallel": true, "self": 10.343622607006182, "children": { "UnityEnvironment._generate_step_input": { "total": 5.450166569993826, "count": 18191, "is_parallel": true, "self": 5.450166569993826 }, "communicator.exchange": { "total": 165.30639116900795, "count": 18191, "is_parallel": true, "self": 165.30639116900795 }, "steps_from_proto": { "total": 36.19815167999582, "count": 18191, "is_parallel": true, "self": 6.5836972729943, "children": { "_process_rank_one_or_two_observation": { "total": 29.614454407001517, "count": 181910, "is_parallel": true, "self": 29.614454407001517 } } } } } } } } } } }, "trainer_advance": { "total": 118.99984757099946, "count": 18192, "self": 0.4549534050073589, "children": { "process_trajectory": { "total": 26.59489391399177, "count": 18192, "self": 26.10053841599165, "children": { "RLTrainer._checkpoint": { "total": 0.49435549800011813, "count": 4, "self": 0.49435549800011813 } } }, "_update_policy": { "total": 91.95000025200034, "count": 90, "self": 37.5723581700031, "children": { "TorchPPOOptimizer.update": { "total": 54.37764208199724, "count": 4587, "self": 54.37764208199724 } } } } } } }, "trainer_threads": { "total": 1.142999963121838e-06, "count": 1, "self": 1.142999963121838e-06 }, "TrainerController._save_models": { "total": 0.0812316289999444, "count": 1, "self": 0.000747893999914595, "children": { "RLTrainer._checkpoint": { "total": 0.08048373500002981, "count": 1, "self": 0.08048373500002981 } } } } } } }