{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5289312601089478, "min": 1.4429744482040405, "max": 1.6524065732955933, "count": 437 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31508.21484375, "min": 10421.470703125, "max": 36688.703125, "count": 437 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 65.6103896103896, "min": 48.48979591836735, "max": 114.5111111111111, "count": 437 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20208.0, "min": 4812.0, "max": 21704.0, "count": 437 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1591.266926676015, "min": 1525.7500144565668, "max": 1634.7649431157508, "count": 437 }, "SoccerTwos.Self-play.ELO.sum": { "value": 245055.1067081063, "min": 60774.17314216623, "max": 313938.9115618683, "count": 437 }, "SoccerTwos.Step.mean": { "value": 18089958.0, "min": 13729936.0, "max": 18089958.0, "count": 437 }, "SoccerTwos.Step.sum": { "value": 18089958.0, "min": 13729936.0, "max": 18089958.0, "count": 437 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.007700234651565552, "min": -0.13673512637615204, "max": 0.07944316416978836, "count": 437 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.178135871887207, "min": -18.185771942138672, "max": 12.552020072937012, "count": 437 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.007211917545646429, "min": -0.13792335987091064, "max": 0.081109918653965, "count": 437 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.1034233570098877, "min": -18.343807220458984, "max": 12.815367698669434, "count": 437 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 437 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 437 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.03309281277500726, "min": -0.3374048784011748, "max": 0.32358507300490763, "count": 437 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -5.063200354576111, "min": -55.334400057792664, "max": 43.36039978265762, "count": 437 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.03309281277500726, "min": -0.3374048784011748, "max": 0.32358507300490763, "count": 437 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -5.063200354576111, "min": -55.334400057792664, "max": 43.36039978265762, "count": 437 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 437 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 437 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019048793388841054, "min": 0.01202231189866628, "max": 0.023315804599163433, "count": 211 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019048793388841054, "min": 0.01202231189866628, "max": 0.023315804599163433, "count": 211 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10422521059711774, "min": 0.07008710379401843, "max": 0.10756902545690536, "count": 211 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10422521059711774, "min": 0.07008710379401843, "max": 0.10756902545690536, "count": 211 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10599818527698517, "min": 0.07135874889791012, "max": 0.10912942091623942, "count": 211 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10599818527698517, "min": 0.07135874889791012, "max": 0.10912942091623942, "count": 211 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 211 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 211 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 211 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 211 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 211 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 211 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1702620132", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/samil/anaconda3/envs/unity/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device cuda", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702627737" }, "total": 7605.147426823, "count": 1, "self": 0.42629649300033634, "children": { "run_training.setup": { "total": 0.044025450999995996, "count": 1, "self": 0.044025450999995996 }, "TrainerController.start_learning": { "total": 7604.677104879, "count": 1, "self": 6.384801841059016, "children": { "TrainerController._reset_env": { "total": 3.543140044001973, "count": 23, "self": 3.543140044001973 }, "TrainerController.advance": { "total": 7594.35423294594, "count": 299615, "self": 6.412759897923934, "children": { "env_step": { "total": 5653.755548863008, "count": 299615, "self": 4278.739194771819, "children": { "SubprocessEnvManager._take_step": { "total": 1370.8643595179715, "count": 299615, "self": 35.6024519718776, "children": { "TorchPolicy.evaluate": { "total": 1335.2619075460939, "count": 548149, "self": 1335.2619075460939 } } }, "workers": { "total": 4.151994573217664, "count": 299614, "self": 0.0, "children": { "worker_root": { "total": 7596.223032310018, "count": 299614, "is_parallel": true, "self": 4014.40834585581, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025739310000005844, "count": 2, "is_parallel": true, "self": 0.001017920999998978, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015560100000016064, "count": 8, "is_parallel": true, "self": 0.0015560100000016064 } } }, "UnityEnvironment.step": { "total": 0.02281602400000793, "count": 1, "is_parallel": true, "self": 0.0005066710000249941, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003378149999946345, "count": 1, "is_parallel": true, "self": 0.0003378149999946345 }, "communicator.exchange": { "total": 0.02049500199998988, "count": 1, "is_parallel": true, "self": 0.02049500199998988 }, "steps_from_proto": { "total": 0.0014765359999984184, "count": 2, "is_parallel": true, "self": 0.0002987140000243471, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011778219999740713, "count": 8, "is_parallel": true, "self": 0.0011778219999740713 } } } } } } }, "steps_from_proto": { "total": 0.03414245899863033, "count": 44, "is_parallel": true, "self": 0.006506948000961188, "children": { "_process_rank_one_or_two_observation": { "total": 0.027635510997669144, "count": 176, "is_parallel": true, "self": 0.027635510997669144 } } }, "UnityEnvironment.step": { "total": 3581.78054399521, "count": 299613, "is_parallel": true, "self": 196.83538217598698, "children": { "UnityEnvironment._generate_step_input": { "total": 106.80310568586641, "count": 299613, "is_parallel": true, "self": 106.80310568586641 }, "communicator.exchange": { "total": 2738.338005463118, "count": 299613, "is_parallel": true, "self": 2738.338005463118 }, "steps_from_proto": { "total": 539.8040506702387, "count": 599226, "is_parallel": true, "self": 100.28991740625202, "children": { "_process_rank_one_or_two_observation": { "total": 439.51413326398665, "count": 2396904, "is_parallel": true, "self": 439.51413326398665 } } } } } } } } } } }, "trainer_advance": { "total": 1934.1859241850077, "count": 299614, "self": 41.93469052002342, "children": { "process_trajectory": { "total": 736.4015649759863, "count": 299614, "self": 733.8347796079853, "children": { "RLTrainer._checkpoint": { "total": 2.5667853680009785, "count": 9, "self": 2.5667853680009785 } } }, "_update_policy": { "total": 1155.849668688998, "count": 211, "self": 526.311828841966, "children": { "TorchPOCAOptimizer.update": { "total": 629.537839847032, "count": 6330, "self": 629.537839847032 } } } } } } }, "trainer_threads": { "total": 1.3119997674948536e-06, "count": 1, "self": 1.3119997674948536e-06 }, "TrainerController._save_models": { "total": 0.3949287359992013, "count": 1, "self": 0.0016341169994120719, "children": { "RLTrainer._checkpoint": { "total": 0.39329461899978924, "count": 1, "self": 0.39329461899978924 } } } } } } }