{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.30172663927078247, "min": 0.30172663927078247, "max": 2.5828857421875, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 15054.9521484375, "min": 15054.9521484375, "max": 130466.71875, "count": 10 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 49936.0, "max": 499976.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 49936.0, "max": 499976.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.4858980178833, "min": 0.4753887355327606, "max": 13.4858980178833, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 13526.35546875, "min": 471.58563232421875, "max": 13526.35546875, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 50347.0, "min": 48158.0, "max": 50347.0, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.703557312252965, "min": 6.198347107438017, "max": 26.703557312252965, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 6756.0, "min": 1500.0, "max": 6756.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.703557312252965, "min": 6.198347107438017, "max": 26.703557312252965, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 6756.0, "min": 1500.0, "max": 6756.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.009090584838607658, "min": 0.005687295296229422, "max": 0.01049920906856035, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.03636233935443063, "min": 0.02843647648114711, "max": 0.045652506688687325, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.22817654473086196, "min": 0.22436410536368684, "max": 0.5847262879212698, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9127061789234479, "min": 0.9127061789234479, "max": 2.923631439606349, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 9.717609514119998e-05, "min": 9.717609514119998e-05, "max": 0.0018945760052712002, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0003887043805647999, "min": 0.0003887043805647999, "max": 0.0085314560734272, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.11943519999999999, "min": 0.11943519999999999, "max": 0.4789152, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.47774079999999997, "min": 0.47774079999999997, "max": 2.2062912000000003, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 5.810212e-05, "min": 5.810212e-05, "max": 0.00094781512, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00023240848, "min": 0.00023240848, "max": 0.00427307072, "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": "1679294412", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/opt/conda/envs/ml2/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+cu115", "numpy_version": "1.21.2", "end_time_seconds": "1679295443" }, "total": 1030.7806049309947, "count": 1, "self": 0.4357619519942091, "children": { "run_training.setup": { "total": 0.017948744003660977, "count": 1, "self": 0.017948744003660977 }, "TrainerController.start_learning": { "total": 1030.3268942349969, "count": 1, "self": 1.1514493724534987, "children": { "TrainerController._reset_env": { "total": 4.673536212001636, "count": 1, "self": 4.673536212001636 }, "TrainerController.advance": { "total": 1024.3582615765408, "count": 45464, "self": 1.329777489299886, "children": { "env_step": { "total": 850.2061516425965, "count": 45464, "self": 583.3694386825518, "children": { "SubprocessEnvManager._take_step": { "total": 266.1118606540185, "count": 45464, "self": 5.375045314474846, "children": { "TorchPolicy.evaluate": { "total": 260.7368153395437, "count": 45464, "self": 260.7368153395437 } } }, "workers": { "total": 0.7248523060261505, "count": 45464, "self": 0.0, "children": { "worker_root": { "total": 1027.3872145959904, "count": 45464, "is_parallel": true, "self": 509.1380840027632, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017432580061722547, "count": 1, "is_parallel": true, "self": 0.0007082269949023612, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010350310112698935, "count": 10, "is_parallel": true, "self": 0.0010350310112698935 } } }, "UnityEnvironment.step": { "total": 0.021732952998718247, "count": 1, "is_parallel": true, "self": 0.00029198699485277757, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000252685000305064, "count": 1, "is_parallel": true, "self": 0.000252685000305064 }, "communicator.exchange": { "total": 0.020313016000727657, "count": 1, "is_parallel": true, "self": 0.020313016000727657 }, "steps_from_proto": { "total": 0.000875265002832748, "count": 1, "is_parallel": true, "self": 0.00020566099556162953, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006696040072711185, "count": 10, "is_parallel": true, "self": 0.0006696040072711185 } } } } } } }, "UnityEnvironment.step": { "total": 518.2491305932272, "count": 45463, "is_parallel": true, "self": 12.405924925646104, "children": { "UnityEnvironment._generate_step_input": { "total": 7.284209254932648, "count": 45463, "is_parallel": true, "self": 7.284209254932648 }, "communicator.exchange": { "total": 464.8894674130206, "count": 45463, "is_parallel": true, "self": 464.8894674130206 }, "steps_from_proto": { "total": 33.6695289996278, "count": 45463, "is_parallel": true, "self": 8.057895610989362, "children": { "_process_rank_one_or_two_observation": { "total": 25.611633388638438, "count": 454630, "is_parallel": true, "self": 25.611633388638438 } } } } } } } } } } }, "trainer_advance": { "total": 172.82233244464442, "count": 45464, "self": 1.4902701629107469, "children": { "process_trajectory": { "total": 77.16832207974221, "count": 45464, "self": 76.94293895274313, "children": { "RLTrainer._checkpoint": { "total": 0.22538312699907692, "count": 1, "self": 0.22538312699907692 } } }, "_update_policy": { "total": 94.16374020199146, "count": 47, "self": 76.68532940502337, "children": { "TorchPPOOptimizer.update": { "total": 17.47841079696809, "count": 282, "self": 17.47841079696809 } } } } } } }, "trainer_threads": { "total": 5.879992386326194e-07, "count": 1, "self": 5.879992386326194e-07 }, "TrainerController._save_models": { "total": 0.1436464860016713, "count": 1, "self": 0.0069262640026863664, "children": { "RLTrainer._checkpoint": { "total": 0.13672022199898493, "count": 1, "self": 0.13672022199898493 } } } } } } }