{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9460203051567078, "min": 0.9460203051567078, "max": 2.8748648166656494, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9053.4140625, "min": 9053.4140625, "max": 29504.73828125, "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": 13.075272560119629, "min": 0.3394435942173004, "max": 13.147194862365723, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2549.67822265625, "min": 65.85205841064453, "max": 2682.02783203125, "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": 0.06850133107817621, "min": 0.062487946852114895, "max": 0.07193992462841789, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27400532431270486, "min": 0.2516205908625624, "max": 0.3596996231420895, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20058498717844486, "min": 0.110084807132736, "max": 0.2777517387533889, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8023399487137794, "min": 0.440339228530944, "max": 1.354405025202854, "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": 25.454545454545453, "min": 3.272727272727273, "max": 26.072727272727274, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 144.0, "max": 1434.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.272727272727273, "max": 26.072727272727274, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 144.0, "max": 1434.0, "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": "1686372194", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1686372635" }, "total": 441.557981015, "count": 1, "self": 0.7455476489998318, "children": { "run_training.setup": { "total": 0.04015457900004549, "count": 1, "self": 0.04015457900004549 }, "TrainerController.start_learning": { "total": 440.7722787870001, "count": 1, "self": 0.4822094559865491, "children": { "TrainerController._reset_env": { "total": 5.384305204000043, "count": 1, "self": 5.384305204000043 }, "TrainerController.advance": { "total": 434.69609987201375, "count": 18221, "self": 0.2319961860159765, "children": { "env_step": { "total": 434.46410368599777, "count": 18221, "self": 314.4516854960036, "children": { "SubprocessEnvManager._take_step": { "total": 119.7824652889924, "count": 18221, "self": 1.6757976649834063, "children": { "TorchPolicy.evaluate": { "total": 118.10666762400899, "count": 18221, "self": 118.10666762400899 } } }, "workers": { "total": 0.22995290100175225, "count": 18221, "self": 0.0, "children": { "worker_root": { "total": 439.22081411099987, "count": 18221, "is_parallel": true, "self": 209.36419820699894, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005936384000051476, "count": 1, "is_parallel": true, "self": 0.00376570200023707, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021706819998144056, "count": 10, "is_parallel": true, "self": 0.0021706819998144056 } } }, "UnityEnvironment.step": { "total": 0.03542080199997599, "count": 1, "is_parallel": true, "self": 0.0006769770001255893, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039752199995746196, "count": 1, "is_parallel": true, "self": 0.00039752199995746196 }, "communicator.exchange": { "total": 0.03222513899993373, "count": 1, "is_parallel": true, "self": 0.03222513899993373 }, "steps_from_proto": { "total": 0.002121163999959208, "count": 1, "is_parallel": true, "self": 0.00041388500017092156, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017072789997882865, "count": 10, "is_parallel": true, "self": 0.0017072789997882865 } } } } } } }, "UnityEnvironment.step": { "total": 229.85661590400093, "count": 18220, "is_parallel": true, "self": 9.910005264008646, "children": { "UnityEnvironment._generate_step_input": { "total": 4.8694456400040735, "count": 18220, "is_parallel": true, "self": 4.8694456400040735 }, "communicator.exchange": { "total": 182.57860946601068, "count": 18220, "is_parallel": true, "self": 182.57860946601068 }, "steps_from_proto": { "total": 32.49855553397754, "count": 18220, "is_parallel": true, "self": 5.763240735962086, "children": { "_process_rank_one_or_two_observation": { "total": 26.73531479801545, "count": 182200, "is_parallel": true, "self": 26.73531479801545 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016643199978716439, "count": 1, "self": 0.00016643199978716439, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 431.36740298395546, "count": 423135, "is_parallel": true, "self": 9.029388310955937, "children": { "process_trajectory": { "total": 236.87442412899975, "count": 423135, "is_parallel": true, "self": 235.26746134199993, "children": { "RLTrainer._checkpoint": { "total": 1.6069627869998158, "count": 4, "is_parallel": true, "self": 1.6069627869998158 } } }, "_update_policy": { "total": 185.46359054399977, "count": 90, "is_parallel": true, "self": 71.38745213299865, "children": { "TorchPPOOptimizer.update": { "total": 114.07613841100112, "count": 4584, "is_parallel": true, "self": 114.07613841100112 } } } } } } } } }, "TrainerController._save_models": { "total": 0.20949782299999242, "count": 1, "self": 0.0010974790000091161, "children": { "RLTrainer._checkpoint": { "total": 0.2084003439999833, "count": 1, "self": 0.2084003439999833 } } } } } } }