{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9110689163208008, "min": 0.9110689163208008, "max": 2.863699197769165, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8698.8857421875, "min": 8698.8857421875, "max": 29327.14453125, "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": 13.083703994750977, "min": 0.356632262468338, "max": 13.083703994750977, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2551.322265625, "min": 69.18666076660156, "max": 2659.88037109375, "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": 0.07157042374873365, "min": 0.0607700728926027, "max": 0.07582205761693116, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2862816949949346, "min": 0.2555481334688118, "max": 0.3791102880846558, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21714748370954218, "min": 0.11662855400080682, "max": 0.2665224395254079, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8685899348381687, "min": 0.4665142160032273, "max": 1.3326121976270393, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.0776097306000009e-05, "min": 1.0776097306000009e-05, "max": 0.000389176002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.3104389224000035e-05, "min": 4.3104389224000035e-05, "max": 0.0018468800382800002, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.197294, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.004864970599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828000000003, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.568181818181817, "min": 2.909090909090909, "max": 25.945454545454545, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1125.0, "min": 128.0, "max": 1427.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.568181818181817, "min": 2.909090909090909, "max": 25.945454545454545, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1125.0, "min": 128.0, "max": 1427.0, "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": "1692233825", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1692234345" }, "total": 519.5496725019999, "count": 1, "self": 0.8405533589998413, "children": { "run_training.setup": { "total": 0.04675179000003027, "count": 1, "self": 0.04675179000003027 }, "TrainerController.start_learning": { "total": 518.662367353, "count": 1, "self": 0.5869617240300613, "children": { "TrainerController._reset_env": { "total": 5.013535607000108, "count": 1, "self": 5.013535607000108 }, "TrainerController.advance": { "total": 512.8255984619697, "count": 18213, "self": 0.2778984619867515, "children": { "env_step": { "total": 512.5476999999829, "count": 18213, "self": 382.32582190201174, "children": { "SubprocessEnvManager._take_step": { "total": 129.93360923999353, "count": 18213, "self": 1.8495164829905661, "children": { "TorchPolicy.evaluate": { "total": 128.08409275700296, "count": 18213, "self": 128.08409275700296 } } }, "workers": { "total": 0.28826885797764135, "count": 18213, "self": 0.0, "children": { "worker_root": { "total": 516.8077590000017, "count": 18213, "is_parallel": true, "self": 260.205909727003, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006433936999997059, "count": 1, "is_parallel": true, "self": 0.00485998099986773, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015739560001293285, "count": 10, "is_parallel": true, "self": 0.0015739560001293285 } } }, "UnityEnvironment.step": { "total": 0.12625377599999865, "count": 1, "is_parallel": true, "self": 0.000615399000139405, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000515685999971538, "count": 1, "is_parallel": true, "self": 0.000515685999971538 }, "communicator.exchange": { "total": 0.11687253799993869, "count": 1, "is_parallel": true, "self": 0.11687253799993869 }, "steps_from_proto": { "total": 0.008250152999949023, "count": 1, "is_parallel": true, "self": 0.006424562999882255, "children": { "_process_rank_one_or_two_observation": { "total": 0.001825590000066768, "count": 10, "is_parallel": true, "self": 0.001825590000066768 } } } } } } }, "UnityEnvironment.step": { "total": 256.6018492729987, "count": 18212, "is_parallel": true, "self": 10.786053988993785, "children": { "UnityEnvironment._generate_step_input": { "total": 5.547683833003248, "count": 18212, "is_parallel": true, "self": 5.547683833003248 }, "communicator.exchange": { "total": 202.70028485099908, "count": 18212, "is_parallel": true, "self": 202.70028485099908 }, "steps_from_proto": { "total": 37.567826600002604, "count": 18212, "is_parallel": true, "self": 6.773057346988367, "children": { "_process_rank_one_or_two_observation": { "total": 30.794769253014238, "count": 182120, "is_parallel": true, "self": 30.794769253014238 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011679400017783337, "count": 1, "self": 0.00011679400017783337, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 509.00852983495315, "count": 458515, "is_parallel": true, "self": 10.40028430988923, "children": { "process_trajectory": { "total": 262.64811645706527, "count": 458515, "is_parallel": true, "self": 261.1999391080651, "children": { "RLTrainer._checkpoint": { "total": 1.4481773490001615, "count": 4, "is_parallel": true, "self": 1.4481773490001615 } } }, "_update_policy": { "total": 235.96012906799865, "count": 90, "is_parallel": true, "self": 97.28714072300693, "children": { "TorchPPOOptimizer.update": { "total": 138.67298834499172, "count": 6116, "is_parallel": true, "self": 138.67298834499172 } } } } } } } } }, "TrainerController._save_models": { "total": 0.23615476600002694, "count": 1, "self": 0.0011687450000863464, "children": { "RLTrainer._checkpoint": { "total": 0.2349860209999406, "count": 1, "self": 0.2349860209999406 } } } } } } }