{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8920056819915771, "min": 0.8920056819915771, "max": 2.847839832305908, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9655.0693359375, "min": 8133.8291015625, "max": 31827.458984375, "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": 3.360323429107666, "min": 0.25281116366386414, "max": 3.374553918838501, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 339.3926696777344, "min": 24.52268409729004, "max": 339.3926696777344, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.365384615384617, "min": 4.0, "max": 26.56, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1371.0, "min": 176.0, "max": 1423.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.365384615384617, "min": 4.0, "max": 26.56, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1371.0, "min": 176.0, "max": 1423.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.047540761303353066, "min": 0.044641229197914065, "max": 0.051767029237762476, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.23770380651676531, "min": 0.1791434840697548, "max": 0.25883514618881237, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.13847568919882175, "min": 0.07153503330191598, "max": 0.1827829159796238, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6923784459941088, "min": 0.2861401332076639, "max": 0.913914579898119, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.488097503999996e-06, "min": 7.488097503999996e-06, "max": 0.0002920740026419999, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.7440487519999984e-05, "min": 3.7440487519999984e-05, "max": 0.0013900080366639998, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10249599999999999, "min": 0.10249599999999999, "max": 0.19735800000000003, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5124799999999999, "min": 0.42978400000000005, "max": 0.963336, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00013455039999999994, "min": 0.00013455039999999994, "max": 0.0048681641999999995, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0006727519999999997, "min": 0.0006727519999999997, "max": 0.0231704664, "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": "1694362327", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --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": "1694362911" }, "total": 583.600179932, "count": 1, "self": 0.424705738999819, "children": { "run_training.setup": { "total": 0.040271712000048865, "count": 1, "self": 0.040271712000048865 }, "TrainerController.start_learning": { "total": 583.1352024810001, "count": 1, "self": 0.6494099940264277, "children": { "TrainerController._reset_env": { "total": 4.687932924000052, "count": 1, "self": 4.687932924000052 }, "TrainerController.advance": { "total": 577.6398468719738, "count": 18356, "self": 0.2868464799651065, "children": { "env_step": { "total": 577.3530003920087, "count": 18356, "self": 370.46875594598623, "children": { "SubprocessEnvManager._take_step": { "total": 206.60218714101325, "count": 18356, "self": 1.6797750560265285, "children": { "TorchPolicy.evaluate": { "total": 204.92241208498672, "count": 18356, "self": 204.92241208498672 } } }, "workers": { "total": 0.28205730500917525, "count": 18356, "self": 0.0, "children": { "worker_root": { "total": 581.5697969669911, "count": 18356, "is_parallel": true, "self": 334.3999187599966, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022547870000835246, "count": 1, "is_parallel": true, "self": 0.0005270829999517446, "children": { "_process_rank_one_or_two_observation": { "total": 0.00172770400013178, "count": 10, "is_parallel": true, "self": 0.00172770400013178 } } }, "UnityEnvironment.step": { "total": 0.10927042999992409, "count": 1, "is_parallel": true, "self": 0.0006206059999840363, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00038260099995568453, "count": 1, "is_parallel": true, "self": 0.00038260099995568453 }, "communicator.exchange": { "total": 0.10682816899998215, "count": 1, "is_parallel": true, "self": 0.10682816899998215 }, "steps_from_proto": { "total": 0.0014390540000022156, "count": 1, "is_parallel": true, "self": 0.00043369000036364014, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010053639996385755, "count": 10, "is_parallel": true, "self": 0.0010053639996385755 } } } } } } }, "UnityEnvironment.step": { "total": 247.16987820699455, "count": 18355, "is_parallel": true, "self": 10.44284237900797, "children": { "UnityEnvironment._generate_step_input": { "total": 5.169266344012158, "count": 18355, "is_parallel": true, "self": 5.169266344012158 }, "communicator.exchange": { "total": 195.99508465898998, "count": 18355, "is_parallel": true, "self": 195.99508465898998 }, "steps_from_proto": { "total": 35.562684824984444, "count": 18355, "is_parallel": true, "self": 6.528902865963801, "children": { "_process_rank_one_or_two_observation": { "total": 29.033781959020644, "count": 183550, "is_parallel": true, "self": 29.033781959020644 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.001049689999945258, "count": 1, "self": 0.001049689999945258, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 578.1794194920101, "count": 10547, "is_parallel": true, "self": 0.324051139013136, "children": { "process_trajectory": { "total": 56.35117638199631, "count": 10547, "is_parallel": true, "self": 54.6480896269959, "children": { "RLTrainer._checkpoint": { "total": 1.7030867550004132, "count": 4, "is_parallel": true, "self": 1.7030867550004132 } } }, "_update_policy": { "total": 521.5041919710006, "count": 91, "is_parallel": true, "self": 242.01861293000502, "children": { "TorchPPOOptimizer.update": { "total": 279.4855790409956, "count": 7280, "is_parallel": true, "self": 279.4855790409956 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15696300099989458, "count": 1, "self": 0.0011381809999875259, "children": { "RLTrainer._checkpoint": { "total": 0.15582481999990705, "count": 1, "self": 0.15582481999990705 } } } } } } }