{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9220046401023865, "min": 0.9127694368362427, "max": 2.8614320755004883, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8813.4423828125, "min": 8813.4423828125, "max": 29303.92578125, "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": 13.18592643737793, "min": 0.3593502342700958, "max": 13.18592643737793, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2571.255615234375, "min": 69.71394348144531, "max": 2652.0615234375, "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": 0.07547369861947349, "min": 0.0629626342370851, "max": 0.07885268331886561, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.30189479447789397, "min": 0.2703355702024233, "max": 0.37110441182021, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19736945073978573, "min": 0.09636757196972658, "max": 0.2900162841175117, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7894778029591429, "min": 0.3854702878789063, "max": 1.4500814205875585, "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": 25.886363636363637, "min": 2.4545454545454546, "max": 26.436363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1139.0, "min": 108.0, "max": 1454.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.886363636363637, "min": 2.4545454545454546, "max": 26.436363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1139.0, "min": 108.0, "max": 1454.0, "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": "1715084685", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715085147" }, "total": 462.131207694, "count": 1, "self": 0.4349608020000346, "children": { "run_training.setup": { "total": 0.05782296399999609, "count": 1, "self": 0.05782296399999609 }, "TrainerController.start_learning": { "total": 461.63842392799995, "count": 1, "self": 0.61119477000085, "children": { "TrainerController._reset_env": { "total": 2.8712746209999978, "count": 1, "self": 2.8712746209999978 }, "TrainerController.advance": { "total": 458.0554988369991, "count": 18199, "self": 0.30772008299567233, "children": { "env_step": { "total": 457.74777875400343, "count": 18199, "self": 300.61291007101045, "children": { "SubprocessEnvManager._take_step": { "total": 156.82928349699725, "count": 18199, "self": 1.483086672996535, "children": { "TorchPolicy.evaluate": { "total": 155.3461968240007, "count": 18199, "self": 155.3461968240007 } } }, "workers": { "total": 0.3055851859957386, "count": 18199, "self": 0.0, "children": { "worker_root": { "total": 460.36808796899794, "count": 18199, "is_parallel": true, "self": 225.96384114799795, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0075479970000174035, "count": 1, "is_parallel": true, "self": 0.005859295999982805, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016887010000345981, "count": 10, "is_parallel": true, "self": 0.0016887010000345981 } } }, "UnityEnvironment.step": { "total": 0.038214461999984906, "count": 1, "is_parallel": true, "self": 0.0007561489999829973, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039375500000460306, "count": 1, "is_parallel": true, "self": 0.00039375500000460306 }, "communicator.exchange": { "total": 0.03492083899999443, "count": 1, "is_parallel": true, "self": 0.03492083899999443 }, "steps_from_proto": { "total": 0.002143719000002875, "count": 1, "is_parallel": true, "self": 0.0004697329999032718, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016739860000996032, "count": 10, "is_parallel": true, "self": 0.0016739860000996032 } } } } } } }, "UnityEnvironment.step": { "total": 234.404246821, "count": 18198, "is_parallel": true, "self": 10.658686583998417, "children": { "UnityEnvironment._generate_step_input": { "total": 5.540305057999717, "count": 18198, "is_parallel": true, "self": 5.540305057999717 }, "communicator.exchange": { "total": 183.4699402430013, "count": 18198, "is_parallel": true, "self": 183.4699402430013 }, "steps_from_proto": { "total": 34.73531493600055, "count": 18198, "is_parallel": true, "self": 6.704290420976577, "children": { "_process_rank_one_or_two_observation": { "total": 28.031024515023972, "count": 181980, "is_parallel": true, "self": 28.031024515023972 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017521699999178963, "count": 1, "self": 0.00017521699999178963, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 452.4993413209879, "count": 690806, "is_parallel": true, "self": 14.362652301004232, "children": { "process_trajectory": { "total": 249.76862369698364, "count": 690806, "is_parallel": true, "self": 249.1376943049837, "children": { "RLTrainer._checkpoint": { "total": 0.6309293919999277, "count": 4, "is_parallel": true, "self": 0.6309293919999277 } } }, "_update_policy": { "total": 188.36806532300005, "count": 90, "is_parallel": true, "self": 55.928949804000524, "children": { "TorchPPOOptimizer.update": { "total": 132.43911551899953, "count": 4587, "is_parallel": true, "self": 132.43911551899953 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10028048300000592, "count": 1, "self": 0.0010356450000017503, "children": { "RLTrainer._checkpoint": { "total": 0.09924483800000417, "count": 1, "self": 0.09924483800000417 } } } } } } }