{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3980586528778076, "min": 1.3634949922561646, "max": 3.2957286834716797, "count": 1923 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27916.435546875, "min": 17922.47265625, "max": 121982.59375, "count": 1923 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.142857142857146, "min": 42.06086956521739, "max": 999.0, "count": 1923 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19708.0, "min": 16296.0, "max": 25048.0, "count": 1923 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1633.4859769363852, "min": 1185.2219053093295, "max": 1675.201217289502, "count": 1915 }, "SoccerTwos.Self-play.ELO.sum": { "value": 297294.4478024221, "min": 2371.7281019661887, "max": 365594.8613591246, "count": 1915 }, "SoccerTwos.Step.mean": { "value": 19229985.0, "min": 9540.0, "max": 19229985.0, "count": 1923 }, "SoccerTwos.Step.sum": { "value": 19229985.0, "min": 9540.0, "max": 19229985.0, "count": 1923 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.007346347905695438, "min": -0.13940945267677307, "max": 0.19194668531417847, "count": 1923 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.3370352983474731, "min": -21.46905517578125, "max": 27.089494705200195, "count": 1923 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.006368838716298342, "min": -0.1394197791814804, "max": 0.18767111003398895, "count": 1923 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.1591286659240723, "min": -21.470645904541016, "max": 25.7528076171875, "count": 1923 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1923 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1923 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.004892306995915843, "min": -0.625, "max": 0.5011166661977768, "count": 1923 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.8903998732566833, "min": -56.993600368499756, "max": 58.75800025463104, "count": 1923 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.004892306995915843, "min": -0.625, "max": 0.5011166661977768, "count": 1923 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.8903998732566833, "min": -56.993600368499756, "max": 58.75800025463104, "count": 1923 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1923 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1923 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01572740066718931, "min": 0.009356382608045048, "max": 0.024892098117076482, "count": 929 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01572740066718931, "min": 0.009356382608045048, "max": 0.024892098117076482, "count": 929 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09969830686847368, "min": 0.00018726339743201, "max": 0.12347314481933912, "count": 929 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09969830686847368, "min": 0.00018726339743201, "max": 0.12347314481933912, "count": 929 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10096026236812274, "min": 0.00018778860685415567, "max": 0.12593497683604557, "count": 929 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10096026236812274, "min": 0.00018778860685415567, "max": 0.12593497683604557, "count": 929 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 929 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 929 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 929 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 929 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 929 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 929 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1736445161", "python_version": "3.10.12 (main, Jan 9 2025, 09:23:36) [Clang 16.0.0 (clang-1600.0.26.6)]", "command_line_arguments": "/Users/hartman23/.pyenv/versions/hugging_face_unit7/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1", "numpy_version": "1.23.5", "end_time_seconds": "1736797963" }, "total": 63518.89755920798, "count": 1, "self": 0.10883466608356684, "children": { "run_training.setup": { "total": 0.058410916943103075, "count": 1, "self": 0.058410916943103075 }, "TrainerController.start_learning": { "total": 63518.730313624954, "count": 1, "self": 11.427141123102047, "children": { "TrainerController._reset_env": { "total": 6.660674122045748, "count": 97, "self": 6.660674122045748 }, "TrainerController.advance": { "total": 63500.46627292177, "count": 1314866, "self": 10.511858905549161, "children": { "env_step": { "total": 52705.449174563866, "count": 1314866, "self": 51124.18154920405, "children": { "SubprocessEnvManager._take_step": { "total": 1573.8389198563527, "count": 1314866, "self": 53.12486745265778, "children": { "TorchPolicy.evaluate": { "total": 1520.714052403695, "count": 2422794, "self": 1520.714052403695 } } }, "workers": { "total": 7.428705503465608, "count": 1314865, "self": 0.0, "children": { "worker_root": { "total": 63498.35339734331, "count": 1314865, "is_parallel": true, "self": 14027.942053620704, "children": { "steps_from_proto": { "total": 0.12692924542352557, "count": 194, "is_parallel": true, "self": 0.016379294567741454, "children": { "_process_rank_one_or_two_observation": { "total": 0.11054995085578412, "count": 776, "is_parallel": true, "self": 0.11054995085578412 } } }, "UnityEnvironment.step": { "total": 49470.28441447718, "count": 1314865, "is_parallel": true, "self": 131.70878516847733, "children": { "UnityEnvironment._generate_step_input": { "total": 910.4375813604565, "count": 1314865, "is_parallel": true, "self": 910.4375813604565 }, "communicator.exchange": { "total": 46831.39487738756, "count": 1314865, "is_parallel": true, "self": 46831.39487738756 }, "steps_from_proto": { "total": 1596.7431705606868, "count": 2629730, "is_parallel": true, "self": 189.29334452899639, "children": { "_process_rank_one_or_two_observation": { "total": 1407.4498260316905, "count": 10518920, "is_parallel": true, "self": 1407.4498260316905 } } } } } } } } } } }, "trainer_advance": { "total": 10784.505239452352, "count": 1314865, "self": 89.22563077264931, "children": { "process_trajectory": { "total": 2218.2159456931986, "count": 1314865, "self": 2211.1133135244017, "children": { "RLTrainer._checkpoint": { "total": 7.102632168796845, "count": 38, "self": 7.102632168796845 } } }, "_update_policy": { "total": 8477.063662986504, "count": 929, "self": 1186.083405618323, "children": { "TorchPOCAOptimizer.update": { "total": 7290.980257368181, "count": 27870, "self": 7290.980257368181 } } } } } } }, "trainer_threads": { "total": 4.5797787606716156e-07, "count": 1, "self": 4.5797787606716156e-07 }, "TrainerController._save_models": { "total": 0.17622500006109476, "count": 1, "self": 0.0035456251353025436, "children": { "RLTrainer._checkpoint": { "total": 0.17267937492579222, "count": 1, "self": 0.17267937492579222 } } } } } } }