{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.8206567764282227, "min": 2.8206567764282227, "max": 2.87654972076416, "count": 2 }, "SnowballTarget.Policy.Entropy.sum": { "value": 28979.427734375, "min": 28979.427734375, "max": 29522.029296875, "count": 2 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 9952.0, "max": 19992.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.2335203886032104, "min": 0.43152570724487305, "max": 1.2335203886032104, "count": 2 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 252.87167358398438, "min": 83.71598815917969, "max": 252.87167358398438, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 2 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07306575977418106, "min": 0.06947016192498269, "max": 0.07306575977418106, "count": 2 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3653287988709053, "min": 0.27788064769993076, "max": 0.3653287988709053, "count": 2 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.16581441955823523, "min": 0.1467732789483396, "max": 0.16581441955823523, "count": 2 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8290720977911762, "min": 0.5870931157933584, "max": 0.8290720977911762, "count": 2 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032007656e-05, "min": 7.032007656e-05, "max": 0.00021882002706000002, "count": 2 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0003516003828, "min": 0.0003516003828, "max": 0.0008752801082400001, "count": 2 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.12344000000000002, "min": 0.12344000000000002, "max": 0.17294, "count": 2 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6172000000000001, "min": 0.6172000000000001, "max": 0.69176, "count": 2 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0011796560000000003, "min": 0.0011796560000000003, "max": 0.003649706, "count": 2 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.005898280000000001, "min": 0.005898280000000001, "max": 0.014598824, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 5.072727272727272, "min": 3.977272727272727, "max": 5.072727272727272, "count": 2 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 279.0, "min": 175.0, "max": 279.0, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 5.072727272727272, "min": 3.977272727272727, "max": 5.072727272727272, "count": 2 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 279.0, "min": 175.0, "max": 279.0, "count": 2 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1686237183", "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": "1686237238" }, "total": 54.44942947000004, "count": 1, "self": 0.4810740089999399, "children": { "run_training.setup": { "total": 0.0421746270001222, "count": 1, "self": 0.0421746270001222 }, "TrainerController.start_learning": { "total": 53.92618083399998, "count": 1, "self": 0.08737422800049899, "children": { "TrainerController._reset_env": { "total": 5.407253598999887, "count": 1, "self": 5.407253598999887 }, "TrainerController.advance": { "total": 48.263694495999744, "count": 1868, "self": 0.028918126996131832, "children": { "env_step": { "total": 48.23477636900361, "count": 1868, "self": 34.9559798360126, "children": { "SubprocessEnvManager._take_step": { "total": 13.250306150994675, "count": 1868, "self": 0.230102326997212, "children": { "TorchPolicy.evaluate": { "total": 13.020203823997463, "count": 1868, "self": 13.020203823997463 } } }, "workers": { "total": 0.02849038199633469, "count": 1868, "self": 0.0, "children": { "worker_root": { "total": 53.61330733299633, "count": 1868, "is_parallel": true, "self": 27.36667204699279, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005435682999859637, "count": 1, "is_parallel": true, "self": 0.003997172000026694, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014385109998329426, "count": 10, "is_parallel": true, "self": 0.0014385109998329426 } } }, "UnityEnvironment.step": { "total": 0.06320941699982541, "count": 1, "is_parallel": true, "self": 0.0005836469997575477, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041339900008097175, "count": 1, "is_parallel": true, "self": 0.00041339900008097175 }, "communicator.exchange": { "total": 0.06015817000002244, "count": 1, "is_parallel": true, "self": 0.06015817000002244 }, "steps_from_proto": { "total": 0.0020542009999644506, "count": 1, "is_parallel": true, "self": 0.0003937789999781671, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016604219999862835, "count": 10, "is_parallel": true, "self": 0.0016604219999862835 } } } } } } }, "UnityEnvironment.step": { "total": 26.24663528600354, "count": 1867, "is_parallel": true, "self": 1.1138610520024486, "children": { "UnityEnvironment._generate_step_input": { "total": 0.556768651000084, "count": 1867, "is_parallel": true, "self": 0.556768651000084 }, "communicator.exchange": { "total": 20.784735134998982, "count": 1867, "is_parallel": true, "self": 20.784735134998982 }, "steps_from_proto": { "total": 3.791270448002024, "count": 1867, "is_parallel": true, "self": 0.7351865909949993, "children": { "_process_rank_one_or_two_observation": { "total": 3.0560838570070246, "count": 18670, "is_parallel": true, "self": 3.0560838570070246 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00028421399997569097, "count": 1, "self": 0.00028421399997569097, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 47.893806459982216, "count": 51047, "is_parallel": true, "self": 1.0741112140149198, "children": { "process_trajectory": { "total": 26.83100033196729, "count": 51047, "is_parallel": true, "self": 26.83100033196729 }, "_update_policy": { "total": 19.988694914000007, "count": 9, "is_parallel": true, "self": 7.200453818995584, "children": { "TorchPPOOptimizer.update": { "total": 12.788241095004423, "count": 456, "is_parallel": true, "self": 12.788241095004423 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1675742969998737, "count": 1, "self": 0.0009010099997794896, "children": { "RLTrainer._checkpoint": { "total": 0.1666732870000942, "count": 1, "self": 0.1666732870000942 } } } } } } }