{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": 0.7742936015129089, "min": 0.7742936015129089, "max": 1.423706293106079, "count": 233 }, "Worm.Policy.Entropy.sum": { "value": 23228.80859375, "min": 23228.80859375, "max": 42711.1875, "count": 233 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 233 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 233 }, "Worm.Step.mean": { "value": 6989000.0, "min": 29000.0, "max": 6989000.0, "count": 233 }, "Worm.Step.sum": { "value": 6989000.0, "min": 29000.0, "max": 6989000.0, "count": 233 }, "Worm.Policy.ExtrinsicValueEstimate.mean": { "value": 242.0957489013672, "min": 0.04105445370078087, "max": 243.65689086914062, "count": 233 }, "Worm.Policy.ExtrinsicValueEstimate.sum": { "value": 7262.87255859375, "min": 1.2316336631774902, "max": 7309.70654296875, "count": 233 }, "Worm.Environment.CumulativeReward.mean": { "value": 1198.4819864908854, "min": 0.22847376391291618, "max": 1222.44765625, "count": 233 }, "Worm.Environment.CumulativeReward.sum": { "value": 35954.45959472656, "min": 6.8542129173874855, "max": 36673.4296875, "count": 233 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 1198.4819864908854, "min": 0.22847376391291618, "max": 1222.44765625, "count": 233 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 35954.45959472656, "min": 6.8542129173874855, "max": 36673.4296875, "count": 233 }, "Worm.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 233 }, "Worm.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 233 }, "Worm.Losses.PolicyLoss.mean": { "value": 0.01606008090467575, "min": 0.011610666393867828, "max": 0.02387814459195527, "count": 232 }, "Worm.Losses.PolicyLoss.sum": { "value": 0.01606008090467575, "min": 0.011610666393867828, "max": 0.02387814459195527, "count": 232 }, "Worm.Losses.ValueLoss.mean": { "value": 13.8456388655163, "min": 0.0014668323315813073, "max": 15.136433987390427, "count": 232 }, "Worm.Losses.ValueLoss.sum": { "value": 13.8456388655163, "min": 0.0014668323315813073, "max": 15.136433987390427, "count": 232 }, "Worm.Policy.LearningRate.mean": { "value": 1.7143851428571302e-06, "min": 1.7143851428571302e-06, "max": 0.00029871428614285713, "count": 232 }, "Worm.Policy.LearningRate.sum": { "value": 1.7143851428571302e-06, "min": 1.7143851428571302e-06, "max": 0.00029871428614285713, "count": 232 }, "Worm.Policy.Epsilon.mean": { "value": 0.10057142857142858, "min": 0.10057142857142858, "max": 0.1995714285714285, "count": 232 }, "Worm.Policy.Epsilon.sum": { "value": 0.10057142857142858, "min": 0.10057142857142858, "max": 0.1995714285714285, "count": 232 }, "Worm.Policy.Beta.mean": { "value": 3.851428571428551e-05, "min": 3.851428571428551e-05, "max": 0.004978614285714285, "count": 232 }, "Worm.Policy.Beta.sum": { "value": 3.851428571428551e-05, "min": 3.851428571428551e-05, "max": 0.004978614285714285, "count": 232 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1657389915", "python_version": "3.8.13 (default, Mar 28 2022, 11:38:47) \n[GCC 7.5.0]", "command_line_arguments": "/home/nm/anaconda3/envs/ml-agents/bin/mlagents-learn ./config/ppo/Worm.yaml --env=./trained-envs-executables/linux/Worm/Worm --run-id=Worm Training --no-graphics --force", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.23.1", "end_time_seconds": "1657395601" }, "total": 5686.2653135269975, "count": 1, "self": 0.21825166399867157, "children": { "run_training.setup": { "total": 0.009958452999853762, "count": 1, "self": 0.009958452999853762 }, "TrainerController.start_learning": { "total": 5686.037103409999, "count": 1, "self": 6.074651844668551, "children": { "TrainerController._reset_env": { "total": 2.3729323570005363, "count": 1, "self": 2.3729323570005363 }, "TrainerController.advance": { "total": 5677.504107482331, "count": 701000, "self": 6.3626116886225645, "children": { "env_step": { "total": 4741.273211906742, "count": 701000, "self": 4258.827497213797, "children": { "SubprocessEnvManager._take_step": { "total": 478.60141630537146, "count": 701000, "self": 30.77560889383858, "children": { "TorchPolicy.evaluate": { "total": 447.8258074115329, "count": 701000, "self": 100.60325676606044, "children": { "TorchPolicy.sample_actions": { "total": 347.22255064547244, "count": 701000, "self": 347.22255064547244 } } } } }, "workers": { "total": 3.844298387573872, "count": 701000, "self": 0.0, "children": { "worker_root": { "total": 5671.579805337637, "count": 701000, "is_parallel": true, "self": 1884.033489645517, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007374469987553312, "count": 1, "is_parallel": true, "self": 0.00021347999791032635, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005239670008450048, "count": 2, "is_parallel": true, "self": 0.0005239670008450048 } } }, "UnityEnvironment.step": { "total": 0.019578467999963323, "count": 1, "is_parallel": true, "self": 0.00017259900050703436, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00033599800008232705, "count": 1, "is_parallel": true, "self": 0.00033599800008232705 }, "communicator.exchange": { "total": 0.018585862999316305, "count": 1, "is_parallel": true, "self": 0.018585862999316305 }, "steps_from_proto": { "total": 0.0004840080000576563, "count": 1, "is_parallel": true, "self": 0.00014713000200572424, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003368779980519321, "count": 2, "is_parallel": true, "self": 0.0003368779980519321 } } } } } } }, "UnityEnvironment.step": { "total": 3787.5463156921196, "count": 700999, "is_parallel": true, "self": 90.06624167344853, "children": { "UnityEnvironment._generate_step_input": { "total": 161.92172522699002, "count": 700999, "is_parallel": true, "self": 161.92172522699002 }, "communicator.exchange": { "total": 3337.9721602264053, "count": 700999, "is_parallel": true, "self": 3337.9721602264053 }, "steps_from_proto": { "total": 197.58618856527573, "count": 700999, "is_parallel": true, "self": 67.12977652093468, "children": { "_process_rank_one_or_two_observation": { "total": 130.45641204434105, "count": 1401998, "is_parallel": true, "self": 130.45641204434105 } } } } } } } } } } }, "trainer_advance": { "total": 929.8682838869663, "count": 701000, "self": 6.682292772185974, "children": { "process_trajectory": { "total": 243.04347511178094, "count": 701000, "self": 241.94448678477966, "children": { "RLTrainer._checkpoint": { "total": 1.0989883270012797, "count": 14, "self": 1.0989883270012797 } } }, "_update_policy": { "total": 680.1425160029994, "count": 233, "self": 585.2013225309984, "children": { "TorchPPOOptimizer.update": { "total": 94.94119347200103, "count": 9786, "self": 94.94119347200103 } } } } } } }, "trainer_threads": { "total": 5.09997335029766e-07, "count": 1, "self": 5.09997335029766e-07 }, "TrainerController._save_models": { "total": 0.08541121600137558, "count": 1, "self": 0.0010737090015027206, "children": { "RLTrainer._checkpoint": { "total": 0.08433750699987286, "count": 1, "self": 0.08433750699987286 } } } } } } }