{ "name": "root", "gauges": { "Worm.Policy.Entropy.mean": { "value": 1.2987080812454224, "min": 1.2987080812454224, "max": 1.4228651523590088, "count": 67 }, "Worm.Policy.Entropy.sum": { "value": 38961.2421875, "min": 38961.2421875, "max": 42685.953125, "count": 67 }, "Worm.Environment.EpisodeLength.mean": { "value": 999.0, "min": 999.0, "max": 999.0, "count": 67 }, "Worm.Environment.EpisodeLength.sum": { "value": 29970.0, "min": 29970.0, "max": 29970.0, "count": 67 }, "Worm.Step.mean": { "value": 2009000.0, "min": 29000.0, "max": 2009000.0, "count": 67 }, "Worm.Step.sum": { "value": 2009000.0, "min": 29000.0, "max": 2009000.0, "count": 67 }, "Worm.Policy.ExtrinsicValueEstimate.mean": { "value": 43.61863327026367, "min": 0.04356028512120247, "max": 43.61863327026367, "count": 67 }, "Worm.Policy.ExtrinsicValueEstimate.sum": { "value": 1308.5589599609375, "min": 1.306808590888977, "max": 1308.5589599609375, "count": 67 }, "Worm.Environment.CumulativeReward.mean": { "value": 243.43898213704426, "min": 0.2854929707944393, "max": 243.43898213704426, "count": 67 }, "Worm.Environment.CumulativeReward.sum": { "value": 7303.169464111328, "min": 8.56478912383318, "max": 7303.169464111328, "count": 67 }, "Worm.Policy.ExtrinsicReward.mean": { "value": 243.43898213704426, "min": 0.2854929707944393, "max": 243.43898213704426, "count": 67 }, "Worm.Policy.ExtrinsicReward.sum": { "value": 7303.169464111328, "min": 8.56478912383318, "max": 7303.169464111328, "count": 67 }, "Worm.IsTraining.mean": { "value": 0.0, "min": 0.0, "max": 1.0, "count": 67 }, "Worm.IsTraining.sum": { "value": 0.0, "min": 0.0, "max": 1.0, "count": 67 }, "Worm.Losses.PolicyLoss.mean": { "value": 0.018084861620861505, "min": 0.013799432956082975, "max": 0.021266230444390594, "count": 66 }, "Worm.Losses.PolicyLoss.sum": { "value": 0.018084861620861505, "min": 0.013799432956082975, "max": 0.021266230444390594, "count": 66 }, "Worm.Losses.ValueLoss.mean": { "value": 3.308221220970154, "min": 0.001292121347172984, "max": 3.6389606169291904, "count": 66 }, "Worm.Losses.ValueLoss.sum": { "value": 3.308221220970154, "min": 0.001292121347172984, "max": 3.6389606169291904, "count": 66 }, "Worm.Policy.LearningRate.mean": { "value": 3.0000990000000026e-06, "min": 3.0000990000000026e-06, "max": 0.00029550000149999997, "count": 66 }, "Worm.Policy.LearningRate.sum": { "value": 3.0000990000000026e-06, "min": 3.0000990000000026e-06, "max": 0.00029550000149999997, "count": 66 }, "Worm.Policy.Epsilon.mean": { "value": 0.101, "min": 0.101, "max": 0.19849999999999998, "count": 66 }, "Worm.Policy.Epsilon.sum": { "value": 0.101, "min": 0.101, "max": 0.19849999999999998, "count": 66 }, "Worm.Policy.Beta.mean": { "value": 5.990000000000004e-05, "min": 5.990000000000004e-05, "max": 0.004925149999999999, "count": 66 }, "Worm.Policy.Beta.sum": { "value": 5.990000000000004e-05, "min": 5.990000000000004e-05, "max": 0.004925149999999999, "count": 66 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704686601", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Worm.yaml --run-id=Worm --no-graphics --force --env=./training-envs-executables/linux/Worm/Worm", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704689190" }, "total": 2588.9252121950003, "count": 1, "self": 0.7347504780004783, "children": { "run_training.setup": { "total": 0.052817630999925314, "count": 1, "self": 0.052817630999925314 }, "TrainerController.start_learning": { "total": 2588.137644086, "count": 1, "self": 3.458534812102698, "children": { "TrainerController._reset_env": { "total": 3.595039046000238, "count": 1, "self": 3.595039046000238 }, "TrainerController.advance": { "total": 2580.9325368488976, "count": 201000, "self": 3.6442257101775795, "children": { "env_step": { "total": 2160.5294379396464, "count": 201000, "self": 1870.1059363813706, "children": { "SubprocessEnvManager._take_step": { "total": 288.13133392122336, "count": 201000, "self": 22.03117165232652, "children": { "TorchPolicy.evaluate": { "total": 266.10016226889684, "count": 201000, "self": 266.10016226889684 } } }, "workers": { "total": 2.2921676370524438, "count": 201000, "self": 0.0, "children": { "worker_root": { "total": 2581.6222336332066, "count": 201000, "is_parallel": true, "self": 967.2939879832711, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007261639998432656, "count": 1, "is_parallel": true, "self": 0.0002271420003125968, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004990219995306688, "count": 2, "is_parallel": true, "self": 0.0004990219995306688 } } }, "UnityEnvironment.step": { "total": 0.06975942200006102, "count": 1, "is_parallel": true, "self": 0.00023476299975300208, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004406830003063078, "count": 1, "is_parallel": true, "self": 0.0004406830003063078 }, "communicator.exchange": { "total": 0.06827202700014823, "count": 1, "is_parallel": true, "self": 0.06827202700014823 }, "steps_from_proto": { "total": 0.0008119489998534846, "count": 1, "is_parallel": true, "self": 0.0004684049995375972, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003435440003158874, "count": 2, "is_parallel": true, "self": 0.0003435440003158874 } } } } } } }, "UnityEnvironment.step": { "total": 1614.3282456499355, "count": 200999, "is_parallel": true, "self": 37.930401863906354, "children": { "UnityEnvironment._generate_step_input": { "total": 65.4865568460491, "count": 200999, "is_parallel": true, "self": 65.4865568460491 }, "communicator.exchange": { "total": 1427.541614172047, "count": 200999, "is_parallel": true, "self": 1427.541614172047 }, "steps_from_proto": { "total": 83.36967276793303, "count": 200999, "is_parallel": true, "self": 27.155472943814402, "children": { "_process_rank_one_or_two_observation": { "total": 56.21419982411862, "count": 401998, "is_parallel": true, "self": 56.21419982411862 } } } } } } } } } } }, "trainer_advance": { "total": 416.7588731990736, "count": 201000, "self": 4.167901946259917, "children": { "process_trajectory": { "total": 96.53525300381489, "count": 201000, "self": 96.07095044581501, "children": { "RLTrainer._checkpoint": { "total": 0.4643025579998721, "count": 4, "self": 0.4643025579998721 } } }, "_update_policy": { "total": 316.0557182489988, "count": 66, "self": 257.98288168299996, "children": { "TorchPPOOptimizer.update": { "total": 58.07283656599884, "count": 2772, "self": 58.07283656599884 } } } } } } }, "trainer_threads": { "total": 1.3679991752724163e-06, "count": 1, "self": 1.3679991752724163e-06 }, "TrainerController._save_models": { "total": 0.15153201100019942, "count": 1, "self": 0.003105984000285389, "children": { "RLTrainer._checkpoint": { "total": 0.14842602699991403, "count": 1, "self": 0.14842602699991403 } } } } } } }