{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.614660382270813, "min": 1.5329911708831787, "max": 3.1653454303741455, "count": 946 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32654.890625, "min": 6200.6533203125, "max": 116047.109375, "count": 946 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 49.21212121212121, "min": 41.33050847457627, "max": 999.0, "count": 946 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19488.0, "min": 3996.0, "max": 31144.0, "count": 946 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1590.3808205730516, "min": 1210.6657767586505, "max": 1619.790326024402, "count": 941 }, "SoccerTwos.Self-play.ELO.sum": { "value": 314895.4024734642, "min": 2424.0827653708648, "max": 377513.0365536685, "count": 941 }, "SoccerTwos.Step.mean": { "value": 9999992.0, "min": 549657.0, "max": 9999992.0, "count": 946 }, "SoccerTwos.Step.sum": { "value": 9999992.0, "min": 549657.0, "max": 9999992.0, "count": 946 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.07650735974311829, "min": -0.11666654795408249, "max": 0.21403224766254425, "count": 946 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -15.22496509552002, "min": -21.466644287109375, "max": 29.588966369628906, "count": 946 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07262206077575684, "min": -0.12031123787164688, "max": 0.2111627459526062, "count": 946 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -14.451789855957031, "min": -22.13726806640625, "max": 29.504426956176758, "count": 946 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 946 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 946 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.16366834197212105, "min": -0.6058875005692244, "max": 0.4048776696029219, "count": 946 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -32.57000005245209, "min": -66.00479984283447, "max": 55.14299935102463, "count": 946 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.16366834197212105, "min": -0.6058875005692244, "max": 0.4048776696029219, "count": 946 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -32.57000005245209, "min": -66.00479984283447, "max": 55.14299935102463, "count": 946 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 946 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 946 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015870315426339706, "min": 0.00968948356846037, "max": 0.0240408629955103, "count": 456 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015870315426339706, "min": 0.00968948356846037, "max": 0.0240408629955103, "count": 456 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10202294091383617, "min": 0.00020218975963265013, "max": 0.12481951639056206, "count": 456 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10202294091383617, "min": 0.00020218975963265013, "max": 0.12481951639056206, "count": 456 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10368427063028017, "min": 0.00021083913209925717, "max": 0.12807482952872912, "count": 456 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10368427063028017, "min": 0.00021083913209925717, "max": 0.12807482952872912, "count": 456 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 456 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 456 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 456 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 456 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 456 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 456 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1735412660", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/kane/miniconda3/envs/soccer_rl/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1735419135" }, "total": 6475.497817641, "count": 1, "self": 0.16737230699072825, "children": { "run_training.setup": { "total": 0.010108270005730446, "count": 1, "self": 0.010108270005730446 }, "TrainerController.start_learning": { "total": 6475.320337064004, "count": 1, "self": 5.83195191447885, "children": { "TrainerController._reset_env": { "total": 1.3394832180274534, "count": 49, "self": 1.3394832180274534 }, "TrainerController.advance": { "total": 6468.083171648497, "count": 651443, "self": 5.450060901894176, "children": { "env_step": { "total": 4922.454020500554, "count": 651443, "self": 3595.986672016901, "children": { "SubprocessEnvManager._take_step": { "total": 1322.9116125044602, "count": 651443, "self": 39.47856949702691, "children": { "TorchPolicy.evaluate": { "total": 1283.4330430074333, "count": 1190364, "self": 1283.4330430074333 } } }, "workers": { "total": 3.555735979192832, "count": 651443, "self": 0.0, "children": { "worker_root": { "total": 6467.586811553083, "count": 651443, "is_parallel": true, "self": 3558.7149287097272, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010675999947125092, "count": 2, "is_parallel": true, "self": 0.0002696989831747487, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007979010115377605, "count": 8, "is_parallel": true, "self": 0.0007979010115377605 } } }, "UnityEnvironment.step": { "total": 0.011551907002285589, "count": 1, "is_parallel": true, "self": 0.00024401399423368275, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021315100457286462, "count": 1, "is_parallel": true, "self": 0.00021315100457286462 }, "communicator.exchange": { "total": 0.010420106002129614, "count": 1, "is_parallel": true, "self": 0.010420106002129614 }, "steps_from_proto": { "total": 0.0006746360013494268, "count": 2, "is_parallel": true, "self": 0.0001330439918092452, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005415920095401816, "count": 8, "is_parallel": true, "self": 0.0005415920095401816 } } } } } } }, "steps_from_proto": { "total": 0.03312732799531659, "count": 96, "is_parallel": true, "self": 0.006399894969945308, "children": { "_process_rank_one_or_two_observation": { "total": 0.026727433025371283, "count": 384, "is_parallel": true, "self": 0.026727433025371283 } } }, "UnityEnvironment.step": { "total": 2908.8387555153604, "count": 651442, "is_parallel": true, "self": 154.0329934919573, "children": { "UnityEnvironment._generate_step_input": { "total": 88.83800150844036, "count": 651442, "is_parallel": true, "self": 88.83800150844036 }, "communicator.exchange": { "total": 2244.097924694048, "count": 651442, "is_parallel": true, "self": 2244.097924694048 }, "steps_from_proto": { "total": 421.8698358209149, "count": 1302884, "is_parallel": true, "self": 78.01466316633741, "children": { "_process_rank_one_or_two_observation": { "total": 343.8551726545775, "count": 5211536, "is_parallel": true, "self": 343.8551726545775 } } } } } } } } } } }, "trainer_advance": { "total": 1540.1790902460489, "count": 651443, "self": 50.01807652482239, "children": { "process_trajectory": { "total": 746.8638942911348, "count": 651443, "self": 745.5166783011227, "children": { "RLTrainer._checkpoint": { "total": 1.347215990012046, "count": 19, "self": 1.347215990012046 } } }, "_update_policy": { "total": 743.2971194300917, "count": 456, "self": 464.1584625707692, "children": { "TorchPOCAOptimizer.update": { "total": 279.1386568593225, "count": 13695, "self": 279.1386568593225 } } } } } } }, "trainer_threads": { "total": 4.0500162867829204e-07, "count": 1, "self": 4.0500162867829204e-07 }, "TrainerController._save_models": { "total": 0.06572987799881957, "count": 1, "self": 0.0008875089988578111, "children": { "RLTrainer._checkpoint": { "total": 0.06484236899996176, "count": 1, "self": 0.06484236899996176 } } } } } } }