{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4065834283828735, "min": 1.3375861644744873, "max": 3.2956738471984863, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 26961.390625, "min": 12303.03515625, "max": 164883.71875, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 63.62820512820513, "min": 41.48275862068966, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19852.0, "min": 15984.0, "max": 23720.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1654.5316384902676, "min": 1196.721825398609, "max": 1728.7768872478168, "count": 4757 }, "SoccerTwos.Self-play.ELO.sum": { "value": 258106.93560448175, "min": 2393.443650797218, "max": 381889.0678337128, "count": 4757 }, "SoccerTwos.Step.mean": { "value": 49999928.0, "min": 9406.0, "max": 49999928.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999928.0, "min": 9406.0, "max": 49999928.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.021992381662130356, "min": -0.13936839997768402, "max": 0.22297438979148865, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.4088191986083984, "min": -23.39931869506836, "max": 33.149871826171875, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.02521267905831337, "min": -0.13752099871635437, "max": 0.22223065793514252, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.9079651832580566, "min": -23.539276123046875, "max": 34.04685974121094, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.07300129167495235, "min": -0.625, "max": 0.5341815584940268, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -11.315200209617615, "min": -65.58839988708496, "max": 75.31959974765778, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.07300129167495235, "min": -0.625, "max": 0.5341815584940268, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -11.315200209617615, "min": -65.58839988708496, "max": 75.31959974765778, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.021906770395192628, "min": 0.010203817345124358, "max": 0.0259513661992969, "count": 2412 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.021906770395192628, "min": 0.010203817345124358, "max": 0.0259513661992969, "count": 2412 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09735843911767006, "min": 5.736197744946973e-08, "max": 0.1262577287852764, "count": 2412 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09735843911767006, "min": 5.736197744946973e-08, "max": 0.1262577287852764, "count": 2412 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0986374740799268, "min": 6.168764805636329e-08, "max": 0.12670502811670303, "count": 2412 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0986374740799268, "min": 6.168764805636329e-08, "max": 0.12670502811670303, "count": 2412 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2412 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2412 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2412 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 2412 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2412 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2412 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701314338", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/opt/conda/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos2 --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701395140" }, "total": 80801.7128439052, "count": 1, "self": 0.2696489712689072, "children": { "run_training.setup": { "total": 0.021462043980136514, "count": 1, "self": 0.021462043980136514 }, "TrainerController.start_learning": { "total": 80801.42173288995, "count": 1, "self": 54.72157657681964, "children": { "TrainerController._reset_env": { "total": 8.037136203842238, "count": 250, "self": 8.037136203842238 }, "TrainerController.advance": { "total": 80738.47926451941, "count": 3422851, "self": 52.8649253314361, "children": { "env_step": { "total": 63502.89614338055, "count": 3422851, "self": 49432.84027358377, "children": { "SubprocessEnvManager._take_step": { "total": 14033.507183132926, "count": 3422851, "self": 350.8056339141913, "children": { "TorchPolicy.evaluate": { "total": 13682.701549218735, "count": 6302376, "self": 13682.701549218735 } } }, "workers": { "total": 36.548686663853005, "count": 3422851, "self": 0.0, "children": { "worker_root": { "total": 80702.99115542881, "count": 3422851, "is_parallel": true, "self": 38289.443041716004, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002285368973389268, "count": 2, "is_parallel": true, "self": 0.00046775350347161293, "children": { "_process_rank_one_or_two_observation": { "total": 0.001817615469917655, "count": 8, "is_parallel": true, "self": 0.001817615469917655 } } }, "UnityEnvironment.step": { "total": 0.026197147089987993, "count": 1, "is_parallel": true, "self": 0.0006329650059342384, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004767240025103092, "count": 1, "is_parallel": true, "self": 0.0004767240025103092 }, "communicator.exchange": { "total": 0.023260981077328324, "count": 1, "is_parallel": true, "self": 0.023260981077328324 }, "steps_from_proto": { "total": 0.0018264770042151213, "count": 2, "is_parallel": true, "self": 0.00030250195413827896, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015239750500768423, "count": 8, "is_parallel": true, "self": 0.0015239750500768423 } } } } } } }, "UnityEnvironment.step": { "total": 42413.0831184343, "count": 3422850, "is_parallel": true, "self": 2031.431441811379, "children": { "UnityEnvironment._generate_step_input": { "total": 1373.0778113040142, "count": 3422850, "is_parallel": true, "self": 1373.0778113040142 }, "communicator.exchange": { "total": 33222.733039091574, "count": 3422850, "is_parallel": true, "self": 33222.733039091574 }, "steps_from_proto": { "total": 5785.84082622733, "count": 6845700, "is_parallel": true, "self": 905.1081427726895, "children": { "_process_rank_one_or_two_observation": { "total": 4880.73268345464, "count": 27382800, "is_parallel": true, "self": 4880.73268345464 } } } } }, "steps_from_proto": { "total": 0.4649952785111964, "count": 498, "is_parallel": true, "self": 0.07368492940440774, "children": { "_process_rank_one_or_two_observation": { "total": 0.39131034910678864, "count": 1992, "is_parallel": true, "self": 0.39131034910678864 } } } } } } } } }, "trainer_advance": { "total": 17182.71819580742, "count": 3422851, "self": 493.9618195865769, "children": { "process_trajectory": { "total": 7407.04453547555, "count": 3422851, "self": 7387.705197133822, "children": { "RLTrainer._checkpoint": { "total": 19.339338341727853, "count": 100, "self": 19.339338341727853 } } }, "_update_policy": { "total": 9281.711840745294, "count": 2412, "self": 6274.685646205675, "children": { "TorchPOCAOptimizer.update": { "total": 3007.0261945396196, "count": 72363, "self": 3007.0261945396196 } } } } } } }, "trainer_threads": { "total": 6.598420441150665e-07, "count": 1, "self": 6.598420441150665e-07 }, "TrainerController._save_models": { "total": 0.18375493003986776, "count": 1, "self": 0.0013503620866686106, "children": { "RLTrainer._checkpoint": { "total": 0.18240456795319915, "count": 1, "self": 0.18240456795319915 } } } } } } }