{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6069731116294861, "min": 0.6069731116294861, "max": 0.8731125593185425, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6216.01171875, "min": 6043.10498046875, "max": 8931.94140625, "count": 10 }, "SnowballTarget.Step.mean": { "value": 299968.0, "min": 209960.0, "max": 299968.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 299968.0, "min": 209960.0, "max": 299968.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.787924766540527, "min": 12.402420043945312, "max": 12.787924766540527, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2608.736572265625, "min": 2368.8623046875, "max": 2617.166015625, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07082948906885862, "min": 0.06274503224333018, "max": 0.07216161539294191, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3541474453442931, "min": 0.2595802312568469, "max": 0.36080807696470957, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23235715253680356, "min": 0.19332557078907447, "max": 0.24652178904005123, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.1617857626840178, "min": 0.7733022831562979, "max": 1.2326089452002562, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.7626764903999992e-05, "min": 1.7626764903999992e-05, "max": 0.000314626735204, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 8.813382451999996e-05, "min": 8.813382451999996e-05, "max": 0.00140813369252, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10176266666666667, "min": 0.10176266666666667, "max": 0.13146266666666664, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5088133333333333, "min": 0.42025066666666666, "max": 0.6408133333333333, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 9.795706666666662e-05, "min": 9.795706666666662e-05, "max": 0.0015799870666666667, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004897853333333331, "min": 0.0004897853333333331, "max": 0.007076585333333335, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.654545454545456, "min": 24.59090909090909, "max": 25.30909090909091, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1356.0, "min": 1082.0, "max": 1392.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.654545454545456, "min": 24.59090909090909, "max": 25.30909090909091, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1356.0, "min": 1082.0, "max": 1392.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1685641856", "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 --resume", "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": "1685642167" }, "total": 310.75539895899965, "count": 1, "self": 0.541311921999295, "children": { "run_training.setup": { "total": 0.04943327000000863, "count": 1, "self": 0.04943327000000863 }, "TrainerController.start_learning": { "total": 310.16465376700035, "count": 1, "self": 0.5631713820112054, "children": { "TrainerController._reset_env": { "total": 0.7570123470004546, "count": 1, "self": 0.7570123470004546 }, "TrainerController.advance": { "total": 308.67696837698895, "count": 9134, "self": 0.229222997963916, "children": { "env_step": { "total": 308.44774537902504, "count": 9134, "self": 251.55290824400618, "children": { "SubprocessEnvManager._take_step": { "total": 56.673169394978686, "count": 9134, "self": 1.3847858530425583, "children": { "TorchPolicy.evaluate": { "total": 55.28838354193613, "count": 9134, "self": 55.28838354193613 } } }, "workers": { "total": 0.22166774004017498, "count": 9134, "self": 0.0, "children": { "worker_root": { "total": 308.8455465819543, "count": 9134, "is_parallel": true, "self": 134.04579592190748, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00589764300002571, "count": 1, "is_parallel": true, "self": 0.0014810439988650614, "children": { "_process_rank_one_or_two_observation": { "total": 0.004416599001160648, "count": 10, "is_parallel": true, "self": 0.004416599001160648 } } }, "UnityEnvironment.step": { "total": 0.04753360500035342, "count": 1, "is_parallel": true, "self": 0.0007310109995160019, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006140080004115589, "count": 1, "is_parallel": true, "self": 0.0006140080004115589 }, "communicator.exchange": { "total": 0.04357211400019878, "count": 1, "is_parallel": true, "self": 0.04357211400019878 }, "steps_from_proto": { "total": 0.002616472000227077, "count": 1, "is_parallel": true, "self": 0.0004719140006272937, "children": { "_process_rank_one_or_two_observation": { "total": 0.002144557999599783, "count": 10, "is_parallel": true, "self": 0.002144557999599783 } } } } } } }, "UnityEnvironment.step": { "total": 174.7997506600468, "count": 9133, "is_parallel": true, "self": 7.31405510814875, "children": { "UnityEnvironment._generate_step_input": { "total": 4.003684717979922, "count": 9133, "is_parallel": true, "self": 4.003684717979922 }, "communicator.exchange": { "total": 139.04099409397804, "count": 9133, "is_parallel": true, "self": 139.04099409397804 }, "steps_from_proto": { "total": 24.441016739940096, "count": 9133, "is_parallel": true, "self": 4.875683104123709, "children": { "_process_rank_one_or_two_observation": { "total": 19.565333635816387, "count": 91330, "is_parallel": true, "self": 19.565333635816387 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0010941059999822755, "count": 1, "self": 0.0010941059999822755, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 306.16741379170253, "count": 308385, "is_parallel": true, "self": 7.195445409645799, "children": { "process_trajectory": { "total": 165.4981269160562, "count": 308385, "is_parallel": true, "self": 164.91818574605713, "children": { "RLTrainer._checkpoint": { "total": 0.5799411699990742, "count": 2, "is_parallel": true, "self": 0.5799411699990742 } } }, "_update_policy": { "total": 133.47384146600052, "count": 45, "is_parallel": true, "self": 46.232917611999255, "children": { "TorchPPOOptimizer.update": { "total": 87.24092385400127, "count": 2292, "is_parallel": true, "self": 87.24092385400127 } } } } } } } } }, "TrainerController._save_models": { "total": 0.16640755499975057, "count": 1, "self": 0.0017855989999588928, "children": { "RLTrainer._checkpoint": { "total": 0.16462195599979168, "count": 1, "self": 0.16462195599979168 } } } } } } }