{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.059171199798584, "min": 3.059171199798584, "max": 3.2957303524017334, "count": 117 }, "SoccerTwos.Policy.Entropy.sum": { "value": 46890.9765625, "min": 8924.302734375, "max": 126969.21875, "count": 117 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 539.8888888888889, "min": 402.6363636363636, "max": 999.0, "count": 117 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19436.0, "min": 7992.0, "max": 28740.0, "count": 117 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1206.1085289211621, "min": 1198.680373626865, "max": 1215.4183054330401, "count": 104 }, "SoccerTwos.Self-play.ELO.sum": { "value": 19297.736462738594, "min": 2402.6316396820293, "max": 19401.48093718411, "count": 104 }, "SoccerTwos.Step.mean": { "value": 1169914.0, "min": 9386.0, "max": 1169914.0, "count": 117 }, "SoccerTwos.Step.sum": { "value": 1169914.0, "min": 9386.0, "max": 1169914.0, "count": 117 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.005314829759299755, "min": -0.06455523520708084, "max": 0.00918043963611126, "count": 117 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.09566693753004074, "min": -1.0327775478363037, "max": 0.14688703417778015, "count": 117 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.006291152909398079, "min": -0.06459656357765198, "max": 0.008282179944217205, "count": 117 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.11324075609445572, "min": -1.0333099365234375, "max": 0.13102498650550842, "count": 117 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 117 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 117 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.23493333160877228, "min": -0.610920000076294, "max": 0.3526499941945076, "count": 117 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.228799968957901, "min": -12.218400001525879, "max": 5.642399907112122, "count": 117 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.23493333160877228, "min": -0.610920000076294, "max": 0.3526499941945076, "count": 117 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.228799968957901, "min": -12.218400001525879, "max": 5.642399907112122, "count": 117 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 117 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 117 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017703200220906486, "min": 0.013049109647302734, "max": 0.020906921201579585, "count": 54 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017703200220906486, "min": 0.013049109647302734, "max": 0.020906921201579585, "count": 54 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.010448992547268669, "min": 0.00020793138343530397, "max": 0.010448992547268669, "count": 54 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.010448992547268669, "min": 0.00020793138343530397, "max": 0.010448992547268669, "count": 54 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.010450880943487088, "min": 0.00021911569056101143, "max": 0.010450880943487088, "count": 54 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.010450880943487088, "min": 0.00021911569056101143, "max": 0.010450880943487088, "count": 54 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 54 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 54 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 54 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 54 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 54 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 54 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1713971955", "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/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713974484" }, "total": 2529.0015541919997, "count": 1, "self": 0.10274598899923149, "children": { "run_training.setup": { "total": 0.057570802000043386, "count": 1, "self": 0.057570802000043386 }, "TrainerController.start_learning": { "total": 2528.8412374010004, "count": 1, "self": 1.7045655339825316, "children": { "TrainerController._reset_env": { "total": 3.587944897999762, "count": 6, "self": 3.587944897999762 }, "TrainerController.advance": { "total": 2523.204093412018, "count": 76412, "self": 1.8903111280574194, "children": { "env_step": { "total": 2062.180577988964, "count": 76412, "self": 1585.9781793540892, "children": { "SubprocessEnvManager._take_step": { "total": 475.11723950589436, "count": 76412, "self": 13.271666741895388, "children": { "TorchPolicy.evaluate": { "total": 461.845572763999, "count": 151622, "self": 461.845572763999 } } }, "workers": { "total": 1.0851591289806493, "count": 76411, "self": 0.0, "children": { "worker_root": { "total": 2524.2408613650623, "count": 76411, "is_parallel": true, "self": 1188.8313308641118, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.008904904000019087, "count": 2, "is_parallel": true, "self": 0.0038840060000779886, "children": { "_process_rank_one_or_two_observation": { "total": 0.0050208979999410985, "count": 8, "is_parallel": true, "self": 0.0050208979999410985 } } }, "UnityEnvironment.step": { "total": 0.04253810400001612, "count": 1, "is_parallel": true, "self": 0.0013427510000383336, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008961439999666254, "count": 1, "is_parallel": true, "self": 0.0008961439999666254 }, "communicator.exchange": { "total": 0.036317191000023286, "count": 1, "is_parallel": true, "self": 0.036317191000023286 }, "steps_from_proto": { "total": 0.003982017999987875, "count": 2, "is_parallel": true, "self": 0.000678803999903721, "children": { "_process_rank_one_or_two_observation": { "total": 0.0033032140000841537, "count": 8, "is_parallel": true, "self": 0.0033032140000841537 } } } } } } }, "UnityEnvironment.step": { "total": 1335.3972622239498, "count": 76410, "is_parallel": true, "self": 84.99141936895694, "children": { "UnityEnvironment._generate_step_input": { "total": 58.67912028001746, "count": 76410, "is_parallel": true, "self": 58.67912028001746 }, "communicator.exchange": { "total": 926.05539542598, "count": 76410, "is_parallel": true, "self": 926.05539542598 }, "steps_from_proto": { "total": 265.6713271489956, "count": 152820, "is_parallel": true, "self": 43.53513674702447, "children": { "_process_rank_one_or_two_observation": { "total": 222.13619040197113, "count": 611280, "is_parallel": true, "self": 222.13619040197113 } } } } }, "steps_from_proto": { "total": 0.01226827700065769, "count": 10, "is_parallel": true, "self": 0.0024873580007351848, "children": { "_process_rank_one_or_two_observation": { "total": 0.009780918999922505, "count": 40, "is_parallel": true, "self": 0.009780918999922505 } } } } } } } } }, "trainer_advance": { "total": 459.13320429499674, "count": 76411, "self": 15.2067951220277, "children": { "process_trajectory": { "total": 132.3577217459707, "count": 76411, "self": 131.73954964797065, "children": { "RLTrainer._checkpoint": { "total": 0.6181720980000591, "count": 2, "self": 0.6181720980000591 } } }, "_update_policy": { "total": 311.56868742699834, "count": 54, "self": 184.2608421800016, "children": { "TorchPOCAOptimizer.update": { "total": 127.30784524699675, "count": 1629, "self": 127.30784524699675 } } } } } } }, "trainer_threads": { "total": 1.5169998732744716e-06, "count": 1, "self": 1.5169998732744716e-06 }, "TrainerController._save_models": { "total": 0.34463203999985126, "count": 1, "self": 0.0030709689999639522, "children": { "RLTrainer._checkpoint": { "total": 0.3415610709998873, "count": 1, "self": 0.3415610709998873 } } } } } } }