{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.5108969211578369, "min": 0.4658852815628052, "max": 2.8535709381103516, "count": 100 }, "SnowballTarget.Policy.Entropy.sum": { "value": 4883.66357421875, "min": 4468.771484375, "max": 29443.14453125, "count": 100 }, "SnowballTarget.Step.mean": { "value": 999952.0, "min": 9952.0, "max": 999952.0, "count": 100 }, "SnowballTarget.Step.sum": { "value": 999952.0, "min": 9952.0, "max": 999952.0, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.901046752929688, "min": 0.35570451617240906, "max": 14.017142295837402, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2710.7041015625, "min": 69.00667572021484, "max": 2866.11474609375, "count": 100 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 100 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06749497934662727, "min": 0.058441346933482144, "max": 0.08094931220768166, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26997991738650906, "min": 0.23376538773392858, "max": 0.4047465610384083, "count": 100 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1554415116780529, "min": 0.13248763733780852, "max": 0.29609571623743747, "count": 100 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6217660467122116, "min": 0.5299505493512341, "max": 1.3781858893001782, "count": 100 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.3764995412000027e-06, "min": 1.3764995412000027e-06, "max": 0.0002983764005411999, "count": 100 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 5.505998164800011e-06, "min": 5.505998164800011e-06, "max": 0.001477032007656, "count": 100 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10045880000000001, "min": 0.10045880000000001, "max": 0.1994588, "count": 100 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40183520000000006, "min": 0.40183520000000006, "max": 0.992344, "count": 100 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.289412000000004e-05, "min": 3.289412000000004e-05, "max": 0.00497299412, "count": 100 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00013157648000000017, "min": 0.00013157648000000017, "max": 0.0246179656, "count": 100 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 27.31111111111111, "min": 3.8863636363636362, "max": 27.886363636363637, "count": 100 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1229.0, "min": 171.0, "max": 1521.0, "count": 100 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 27.31111111111111, "min": 3.8863636363636362, "max": 27.886363636363637, "count": 100 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1229.0, "min": 171.0, "max": 1521.0, "count": 100 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1693492376", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/yaohua/miniconda3/envs/drl/bin/mlagents-learn ./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": "2.1.0.dev20230830", "numpy_version": "1.21.2", "end_time_seconds": "1693493215" }, "total": 839.0474356520008, "count": 1, "self": 0.21955208200051857, "children": { "run_training.setup": { "total": 0.0138591049999377, "count": 1, "self": 0.0138591049999377 }, "TrainerController.start_learning": { "total": 838.8140244650003, "count": 1, "self": 1.4474269238817215, "children": { "TrainerController._reset_env": { "total": 0.9954357389997313, "count": 1, "self": 0.9954357389997313 }, "TrainerController.advance": { "total": 836.3384372451183, "count": 90940, "self": 0.6931914400829555, "children": { "env_step": { "total": 835.6452458050353, "count": 90940, "self": 654.5660972306268, "children": { "SubprocessEnvManager._take_step": { "total": 180.35133798014976, "count": 90940, "self": 3.391277875209198, "children": { "TorchPolicy.evaluate": { "total": 176.96006010494057, "count": 90940, "self": 176.96006010494057 } } }, "workers": { "total": 0.727810594258699, "count": 90940, "self": 0.0, "children": { "worker_root": { "total": 837.2192197077948, "count": 90940, "is_parallel": true, "self": 400.5888964957867, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0014959119998820825, "count": 1, "is_parallel": true, "self": 0.0007952880005177576, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007006239993643248, "count": 10, "is_parallel": true, "self": 0.0007006239993643248 } } }, "UnityEnvironment.step": { "total": 0.014676388000225415, "count": 1, "is_parallel": true, "self": 0.00022763799825042952, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00015491800149902701, "count": 1, "is_parallel": true, "self": 0.00015491800149902701 }, "communicator.exchange": { "total": 0.01372803800040856, "count": 1, "is_parallel": true, "self": 0.01372803800040856 }, "steps_from_proto": { "total": 0.0005657940000673989, "count": 1, "is_parallel": true, "self": 0.00012868400335719343, "children": { "_process_rank_one_or_two_observation": { "total": 0.00043710999671020545, "count": 10, "is_parallel": true, "self": 0.00043710999671020545 } } } } } } }, "UnityEnvironment.step": { "total": 436.6303232120081, "count": 90939, "is_parallel": true, "self": 18.784817203950297, "children": { "UnityEnvironment._generate_step_input": { "total": 11.598312497029838, "count": 90939, "is_parallel": true, "self": 11.598312497029838 }, "communicator.exchange": { "total": 346.7528841039548, "count": 90939, "is_parallel": true, "self": 346.7528841039548 }, "steps_from_proto": { "total": 59.49430940707316, "count": 90939, "is_parallel": true, "self": 12.36771396288168, "children": { "_process_rank_one_or_two_observation": { "total": 47.12659544419148, "count": 909390, "is_parallel": true, "self": 47.12659544419148 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00020623100135708228, "count": 1, "self": 0.00020623100135708228, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 836.0283011931551, "count": 441343, "is_parallel": true, "self": 4.382901343522462, "children": { "process_trajectory": { "total": 455.9393077366294, "count": 441343, "is_parallel": true, "self": 454.8024046956307, "children": { "RLTrainer._checkpoint": { "total": 1.1369030409987317, "count": 20, "is_parallel": true, "self": 1.1369030409987317 } } }, "_update_policy": { "total": 375.70609211300325, "count": 454, "is_parallel": true, "self": 104.29007867617474, "children": { "TorchPPOOptimizer.update": { "total": 271.4160134368285, "count": 23151, "is_parallel": true, "self": 271.4160134368285 } } } } } } } } }, "TrainerController._save_models": { "total": 0.03251832599926274, "count": 1, "self": 0.0005257779994281009, "children": { "RLTrainer._checkpoint": { "total": 0.03199254799983464, "count": 1, "self": 0.03199254799983464 } } } } } } }