{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.994994044303894, "min": 0.994994044303894, "max": 2.8665289878845215, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9533.0380859375, "min": 9533.0380859375, "max": 29419.1875, "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": 12.087479591369629, "min": 0.3432791531085968, "max": 12.087479591369629, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2357.05859375, "min": 66.59615325927734, "max": 2427.16650390625, "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": 0.07540443580935471, "min": 0.0598281088414118, "max": 0.07540443580935471, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.30161774323741886, "min": 0.2393124353656472, "max": 0.35722031240851826, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20790054853640352, "min": 0.12349428152939415, "max": 0.2745208202039494, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8316021941456141, "min": 0.4939771261175766, "max": 1.3726041010197472, "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": 24.363636363636363, "min": 3.4545454545454546, "max": 24.363636363636363, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1072.0, "min": 152.0, "max": 1299.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.363636363636363, "min": 3.4545454545454546, "max": 24.363636363636363, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1072.0, "min": 152.0, "max": 1299.0, "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": "1689955518", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "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": "1689956009" }, "total": 491.61683905000007, "count": 1, "self": 0.4813031990000809, "children": { "run_training.setup": { "total": 0.03102718399998139, "count": 1, "self": 0.03102718399998139 }, "TrainerController.start_learning": { "total": 491.104508667, "count": 1, "self": 0.595454607989268, "children": { "TrainerController._reset_env": { "total": 4.168545473999984, "count": 1, "self": 4.168545473999984 }, "TrainerController.advance": { "total": 486.1936953730109, "count": 18204, "self": 0.2910595539866563, "children": { "env_step": { "total": 485.9026358190242, "count": 18204, "self": 355.01148723403105, "children": { "SubprocessEnvManager._take_step": { "total": 130.5929187510054, "count": 18204, "self": 1.8716209960023207, "children": { "TorchPolicy.evaluate": { "total": 128.7212977550031, "count": 18204, "self": 128.7212977550031 } } }, "workers": { "total": 0.2982298339877616, "count": 18204, "self": 0.0, "children": { "worker_root": { "total": 489.41824136400555, "count": 18204, "is_parallel": true, "self": 229.82921234701178, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00203231400007553, "count": 1, "is_parallel": true, "self": 0.0006477400002040667, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013845739998714635, "count": 10, "is_parallel": true, "self": 0.0013845739998714635 } } }, "UnityEnvironment.step": { "total": 0.08819944599997598, "count": 1, "is_parallel": true, "self": 0.0006209959999523562, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003862449999587625, "count": 1, "is_parallel": true, "self": 0.0003862449999587625 }, "communicator.exchange": { "total": 0.08325716600006672, "count": 1, "is_parallel": true, "self": 0.08325716600006672 }, "steps_from_proto": { "total": 0.003935038999998142, "count": 1, "is_parallel": true, "self": 0.0006927840001935692, "children": { "_process_rank_one_or_two_observation": { "total": 0.0032422549998045724, "count": 10, "is_parallel": true, "self": 0.0032422549998045724 } } } } } } }, "UnityEnvironment.step": { "total": 259.5890290169938, "count": 18203, "is_parallel": true, "self": 10.75375204195825, "children": { "UnityEnvironment._generate_step_input": { "total": 5.588737682021701, "count": 18203, "is_parallel": true, "self": 5.588737682021701 }, "communicator.exchange": { "total": 206.00691019098724, "count": 18203, "is_parallel": true, "self": 206.00691019098724 }, "steps_from_proto": { "total": 37.23962910202658, "count": 18203, "is_parallel": true, "self": 6.983331096064148, "children": { "_process_rank_one_or_two_observation": { "total": 30.256298005962435, "count": 182030, "is_parallel": true, "self": 30.256298005962435 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012892399990960257, "count": 1, "self": 0.00012892399990960257, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 482.33051117596074, "count": 461465, "is_parallel": true, "self": 10.539355403961622, "children": { "process_trajectory": { "total": 265.61634821299856, "count": 461465, "is_parallel": true, "self": 264.8113386689985, "children": { "RLTrainer._checkpoint": { "total": 0.805009544000086, "count": 4, "is_parallel": true, "self": 0.805009544000086 } } }, "_update_policy": { "total": 206.17480755900056, "count": 90, "is_parallel": true, "self": 82.40695890500172, "children": { "TorchPPOOptimizer.update": { "total": 123.76784865399884, "count": 4587, "is_parallel": true, "self": 123.76784865399884 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14668428799996036, "count": 1, "self": 0.0010634370000843774, "children": { "RLTrainer._checkpoint": { "total": 0.14562085099987598, "count": 1, "self": 0.14562085099987598 } } } } } } }