{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.8689281940460205, "min": 2.8689281940460205, "max": 2.8902933597564697, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 27392.525390625, "min": 27392.525390625, "max": 29818.1484375, "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": 0.9892514944076538, "min": 0.3205322027206421, "max": 1.0140447616577148, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 192.90403747558594, "min": 62.18324661254883, "max": 199.4861602783203, "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": 0.06810954041144464, "min": 0.06144986330958394, "max": 0.0721037247916961, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27243816164577855, "min": 0.25789434392537064, "max": 0.3605186239584805, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1487379377233047, "min": 0.08012844467827795, "max": 0.1487379377233047, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5949517508932188, "min": 0.3205137787131118, "max": 0.6240584700599653, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.694973060000002e-07, "min": 2.694973060000002e-07, "max": 9.729402706e-06, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.0779892240000008e-06, "min": 1.0779892240000008e-06, "max": 4.617203828000001e-05, "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": 5.295454545454546, "min": 2.340909090909091, "max": 5.295454545454546, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 233.0, "min": 103.0, "max": 233.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 5.295454545454546, "min": 2.340909090909091, "max": 5.295454545454546, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 233.0, "min": 103.0, "max": 233.0, "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": "1720181376", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget.yaml --env=/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1720181847" }, "total": 471.08496546900005, "count": 1, "self": 0.4334756099999595, "children": { "run_training.setup": { "total": 0.05208860800007642, "count": 1, "self": 0.05208860800007642 }, "TrainerController.start_learning": { "total": 470.599401251, "count": 1, "self": 0.5820573039916326, "children": { "TrainerController._reset_env": { "total": 3.4661639149999246, "count": 1, "self": 3.4661639149999246 }, "TrainerController.advance": { "total": 466.44684607600834, "count": 18201, "self": 0.2798414810192753, "children": { "env_step": { "total": 466.16700459498907, "count": 18201, "self": 302.23275107596487, "children": { "SubprocessEnvManager._take_step": { "total": 163.63877712200633, "count": 18201, "self": 1.5726121020115897, "children": { "TorchPolicy.evaluate": { "total": 162.06616501999474, "count": 18201, "self": 162.06616501999474 } } }, "workers": { "total": 0.29547639701786466, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 469.27917230800017, "count": 18201, "is_parallel": true, "self": 238.6657885919917, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0065386559999751626, "count": 1, "is_parallel": true, "self": 0.0042563759998301975, "children": { "_process_rank_one_or_two_observation": { "total": 0.002282280000144965, "count": 10, "is_parallel": true, "self": 0.002282280000144965 } } }, "UnityEnvironment.step": { "total": 0.037079682000012326, "count": 1, "is_parallel": true, "self": 0.000664730000153213, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040437899997414206, "count": 1, "is_parallel": true, "self": 0.00040437899997414206 }, "communicator.exchange": { "total": 0.03389835600000879, "count": 1, "is_parallel": true, "self": 0.03389835600000879 }, "steps_from_proto": { "total": 0.002112216999876182, "count": 1, "is_parallel": true, "self": 0.00042878799990830885, "children": { "_process_rank_one_or_two_observation": { "total": 0.001683428999967873, "count": 10, "is_parallel": true, "self": 0.001683428999967873 } } } } } } }, "UnityEnvironment.step": { "total": 230.61338371600846, "count": 18200, "is_parallel": true, "self": 10.564425119021053, "children": { "UnityEnvironment._generate_step_input": { "total": 5.5528181679992485, "count": 18200, "is_parallel": true, "self": 5.5528181679992485 }, "communicator.exchange": { "total": 179.0419371189937, "count": 18200, "is_parallel": true, "self": 179.0419371189937 }, "steps_from_proto": { "total": 35.454203309994455, "count": 18200, "is_parallel": true, "self": 6.715043611962301, "children": { "_process_rank_one_or_two_observation": { "total": 28.739159698032154, "count": 182000, "is_parallel": true, "self": 28.739159698032154 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011796900002991606, "count": 1, "self": 0.00011796900002991606, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 460.822435876938, "count": 670473, "is_parallel": true, "self": 15.043554974937706, "children": { "process_trajectory": { "total": 255.47930644900293, "count": 670473, "is_parallel": true, "self": 254.7742942270031, "children": { "RLTrainer._checkpoint": { "total": 0.7050122219998229, "count": 4, "is_parallel": true, "self": 0.7050122219998229 } } }, "_update_policy": { "total": 190.29957445299738, "count": 90, "is_parallel": true, "self": 57.934493885996744, "children": { "TorchPPOOptimizer.update": { "total": 132.36508056700063, "count": 4587, "is_parallel": true, "self": 132.36508056700063 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10421598700008872, "count": 1, "self": 0.0014207420001639548, "children": { "RLTrainer._checkpoint": { "total": 0.10279524499992476, "count": 1, "self": 0.10279524499992476 } } } } } } }