{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.1100856065750122, "min": 1.1100856065750122, "max": 2.8630635738372803, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10611.30859375, "min": 10611.30859375, "max": 29352.12890625, "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": 12.924163818359375, "min": 0.37481459975242615, "max": 12.924163818359375, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2520.2119140625, "min": 72.71403503417969, "max": 2620.078857421875, "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.Losses.PolicyLoss.mean": { "value": 0.07698376986491876, "min": 0.0640268919720827, "max": 0.07838202286774165, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.307935079459675, "min": 0.2590665726479618, "max": 0.38168329732519957, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18811904850835892, "min": 0.1493951252835127, "max": 0.27760386338420945, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7524761940334357, "min": 0.5975805011340508, "max": 1.3880193169210473, "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.CumulativeReward.mean": { "value": 25.09090909090909, "min": 3.9318181818181817, "max": 25.654545454545456, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1104.0, "min": 173.0, "max": 1411.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.09090909090909, "min": 3.9318181818181817, "max": 25.654545454545456, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1104.0, "min": 173.0, "max": 1411.0, "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": "1683159511", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1683159975" }, "total": 463.9959471100001, "count": 1, "self": 0.43568439800026226, "children": { "run_training.setup": { "total": 0.03863894699998127, "count": 1, "self": 0.03863894699998127 }, "TrainerController.start_learning": { "total": 463.52162376499984, "count": 1, "self": 0.538131555002451, "children": { "TrainerController._reset_env": { "total": 4.938717792000034, "count": 1, "self": 4.938717792000034 }, "TrainerController.advance": { "total": 457.9009447809974, "count": 18202, "self": 0.26281299798984037, "children": { "env_step": { "total": 457.63813178300757, "count": 18202, "self": 332.77813930600166, "children": { "SubprocessEnvManager._take_step": { "total": 124.59639079900103, "count": 18202, "self": 1.68128407400593, "children": { "TorchPolicy.evaluate": { "total": 122.9151067249951, "count": 18202, "self": 122.9151067249951 } } }, "workers": { "total": 0.2636016780048749, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 462.10985756600087, "count": 18202, "is_parallel": true, "self": 216.57142284600127, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005467876000011529, "count": 1, "is_parallel": true, "self": 0.0031974329997410678, "children": { "_process_rank_one_or_two_observation": { "total": 0.002270443000270461, "count": 10, "is_parallel": true, "self": 0.002270443000270461 } } }, "UnityEnvironment.step": { "total": 0.04662925100001303, "count": 1, "is_parallel": true, "self": 0.000719105999905878, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004875240000501435, "count": 1, "is_parallel": true, "self": 0.0004875240000501435 }, "communicator.exchange": { "total": 0.042437436999989586, "count": 1, "is_parallel": true, "self": 0.042437436999989586 }, "steps_from_proto": { "total": 0.00298518400006742, "count": 1, "is_parallel": true, "self": 0.0010605290001421963, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019246549999252238, "count": 10, "is_parallel": true, "self": 0.0019246549999252238 } } } } } } }, "UnityEnvironment.step": { "total": 245.5384347199996, "count": 18201, "is_parallel": true, "self": 9.678301987995383, "children": { "UnityEnvironment._generate_step_input": { "total": 5.378408700006503, "count": 18201, "is_parallel": true, "self": 5.378408700006503 }, "communicator.exchange": { "total": 196.33981776899464, "count": 18201, "is_parallel": true, "self": 196.33981776899464 }, "steps_from_proto": { "total": 34.14190626300308, "count": 18201, "is_parallel": true, "self": 6.639797827981852, "children": { "_process_rank_one_or_two_observation": { "total": 27.502108435021228, "count": 182010, "is_parallel": true, "self": 27.502108435021228 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001526900000499154, "count": 1, "self": 0.0001526900000499154, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 454.5342445949815, "count": 417349, "is_parallel": true, "self": 9.3911375990549, "children": { "process_trajectory": { "total": 250.60915325092662, "count": 417349, "is_parallel": true, "self": 249.85856867992652, "children": { "RLTrainer._checkpoint": { "total": 0.750584571000104, "count": 4, "is_parallel": true, "self": 0.750584571000104 } } }, "_update_policy": { "total": 194.53395374499996, "count": 90, "is_parallel": true, "self": 74.79280768099977, "children": { "TorchPPOOptimizer.update": { "total": 119.74114606400019, "count": 4587, "is_parallel": true, "self": 119.74114606400019 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14367694699990352, "count": 1, "self": 0.0008958220000749861, "children": { "RLTrainer._checkpoint": { "total": 0.14278112499982853, "count": 1, "self": 0.14278112499982853 } } } } } } }