{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6014095544815063, "min": 0.5497132539749146, "max": 2.8476479053497314, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 5768.720703125, "min": 5348.1845703125, "max": 29068.7890625, "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": 13.678670883178711, "min": 0.2809641361236572, "max": 13.78834342956543, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2804.12744140625, "min": 54.507041931152344, "max": 2826.6103515625, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07110400560846114, "min": 0.06135523216102693, "max": 0.07584322121692821, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3555200280423057, "min": 0.2535353127422436, "max": 0.3700703021481875, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16990783582715424, "min": 0.1216664518316404, "max": 0.29607786016136994, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8495391791357713, "min": 0.4866658073265616, "max": 1.4803893008068496, "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": 26.545454545454547, "min": 3.227272727272727, "max": 27.10909090909091, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1460.0, "min": 142.0, "max": 1491.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.545454545454547, "min": 3.227272727272727, "max": 27.10909090909091, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1460.0, "min": 142.0, "max": 1491.0, "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": "1745436989", "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": "2.7.0+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1745438070" }, "total": 1080.348461854, "count": 1, "self": 0.43614088500021353, "children": { "run_training.setup": { "total": 0.024447172000009232, "count": 1, "self": 0.024447172000009232 }, "TrainerController.start_learning": { "total": 1079.8878737969999, "count": 1, "self": 0.8635908239834862, "children": { "TrainerController._reset_env": { "total": 3.1418069720000403, "count": 1, "self": 3.1418069720000403 }, "TrainerController.advance": { "total": 1075.7990596000166, "count": 45464, "self": 0.9586739229800969, "children": { "env_step": { "total": 768.3817866470037, "count": 45464, "self": 585.2217738739996, "children": { "SubprocessEnvManager._take_step": { "total": 182.60874541602527, "count": 45464, "self": 3.247004577018174, "children": { "TorchPolicy.evaluate": { "total": 179.3617408390071, "count": 45464, "self": 179.3617408390071 } } }, "workers": { "total": 0.5512673569787694, "count": 45464, "self": 0.0, "children": { "worker_root": { "total": 1076.8183809269945, "count": 45464, "is_parallel": true, "self": 563.6837356850127, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005136639999932413, "count": 1, "is_parallel": true, "self": 0.0035971639997569582, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015394760001754548, "count": 10, "is_parallel": true, "self": 0.0015394760001754548 } } }, "UnityEnvironment.step": { "total": 0.03511745900004826, "count": 1, "is_parallel": true, "self": 0.000601634000076956, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004071309999744699, "count": 1, "is_parallel": true, "self": 0.0004071309999744699 }, "communicator.exchange": { "total": 0.032049449000055574, "count": 1, "is_parallel": true, "self": 0.032049449000055574 }, "steps_from_proto": { "total": 0.0020592449999412565, "count": 1, "is_parallel": true, "self": 0.0004055459996834543, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016536990002578023, "count": 10, "is_parallel": true, "self": 0.0016536990002578023 } } } } } } }, "UnityEnvironment.step": { "total": 513.1346452419817, "count": 45463, "is_parallel": true, "self": 24.622568475961202, "children": { "UnityEnvironment._generate_step_input": { "total": 13.777937514009409, "count": 45463, "is_parallel": true, "self": 13.777937514009409 }, "communicator.exchange": { "total": 393.77044199799616, "count": 45463, "is_parallel": true, "self": 393.77044199799616 }, "steps_from_proto": { "total": 80.96369725401496, "count": 45463, "is_parallel": true, "self": 14.64585195508846, "children": { "_process_rank_one_or_two_observation": { "total": 66.3178452989265, "count": 454630, "is_parallel": true, "self": 66.3178452989265 } } } } } } } } } } }, "trainer_advance": { "total": 306.45859903003293, "count": 45464, "self": 1.0834267260352135, "children": { "process_trajectory": { "total": 67.93309371699922, "count": 45464, "self": 66.88661143999946, "children": { "RLTrainer._checkpoint": { "total": 1.0464822769997681, "count": 10, "self": 1.0464822769997681 } } }, "_update_policy": { "total": 237.4420785869985, "count": 227, "self": 95.60625503999302, "children": { "TorchPPOOptimizer.update": { "total": 141.83582354700548, "count": 11574, "self": 141.83582354700548 } } } } } } }, "trainer_threads": { "total": 8.879999313649023e-07, "count": 1, "self": 8.879999313649023e-07 }, "TrainerController._save_models": { "total": 0.0834155129998635, "count": 1, "self": 0.0008181109999441105, "children": { "RLTrainer._checkpoint": { "total": 0.08259740199991938, "count": 1, "self": 0.08259740199991938 } } } } } } }