{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9039276838302612, "min": 1.877668023109436, "max": 3.295680046081543, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37652.07421875, "min": 21336.181640625, "max": 130535.8125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.188235294117646, "min": 44.5462962962963, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19444.0, "min": 12188.0, "max": 28804.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1605.430941467209, "min": 1201.3631874491753, "max": 1617.9638257587087, "count": 482 }, "SoccerTwos.Self-play.ELO.sum": { "value": 272923.26004942553, "min": 2403.3855685662347, "max": 337426.73746828083, "count": 482 }, "SoccerTwos.Step.mean": { "value": 4999886.0, "min": 9340.0, "max": 4999886.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999886.0, "min": 9340.0, "max": 4999886.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.020678412169218063, "min": -0.07728685438632965, "max": 0.21730740368366241, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 3.536008596420288, "min": -13.447912216186523, "max": 35.001216888427734, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.01950807310640812, "min": -0.07330154627561569, "max": 0.22029457986354828, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 3.3358805179595947, "min": -12.974373817443848, "max": 35.57990264892578, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.04291695809503745, "min": -0.5942999999970198, "max": 0.5516645145672624, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -7.338799834251404, "min": -52.972399950027466, "max": 51.914800226688385, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.04291695809503745, "min": -0.5942999999970198, "max": 0.5516645145672624, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -7.338799834251404, "min": -52.972399950027466, "max": 51.914800226688385, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01564950564255317, "min": 0.010274977547912083, "max": 0.026397741365750942, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01564950564255317, "min": 0.010274977547912083, "max": 0.026397741365750942, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10047700678308805, "min": 5.6377131719879496e-05, "max": 0.11392703180511793, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10047700678308805, "min": 5.6377131719879496e-05, "max": 0.11392703180511793, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10159825185934702, "min": 5.571924799975629e-05, "max": 0.1150806521375974, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10159825185934702, "min": 5.571924799975629e-05, "max": 0.1150806521375974, "count": 239 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1742483849", "python_version": "3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]", "command_line_arguments": "/home/dbarbashin/venvs_user/rl_huggi/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos4 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1742491041" }, "total": 7192.425266573002, "count": 1, "self": 0.16784278600243852, "children": { "run_training.setup": { "total": 0.01070069900015369, "count": 1, "self": 0.01070069900015369 }, "TrainerController.start_learning": { "total": 7192.246723087999, "count": 1, "self": 4.643179637234425, "children": { "TrainerController._reset_env": { "total": 1.81035199193866, "count": 25, "self": 1.81035199193866 }, "TrainerController.advance": { "total": 7185.636096144852, "count": 337463, "self": 4.30183144134935, "children": { "env_step": { "total": 5840.249955219246, "count": 337463, "self": 3520.3181815179705, "children": { "SubprocessEnvManager._take_step": { "total": 2316.8116518641473, "count": 337463, "self": 27.630966091674054, "children": { "TorchPolicy.evaluate": { "total": 2289.180685772473, "count": 633458, "self": 2289.180685772473 } } }, "workers": { "total": 3.1201218371279538, "count": 337463, "self": 0.0, "children": { "worker_root": { "total": 7183.342866331164, "count": 337463, "is_parallel": true, "self": 4136.52341552946, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017675779818091542, "count": 2, "is_parallel": true, "self": 0.0004682459984906018, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012993319833185524, "count": 8, "is_parallel": true, "self": 0.0012993319833185524 } } }, "UnityEnvironment.step": { "total": 0.017102126992540434, "count": 1, "is_parallel": true, "self": 0.00028628596919588745, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002130670181941241, "count": 1, "is_parallel": true, "self": 0.0002130670181941241 }, "communicator.exchange": { "total": 0.015769421006552875, "count": 1, "is_parallel": true, "self": 0.015769421006552875 }, "steps_from_proto": { "total": 0.0008333529985975474, "count": 2, "is_parallel": true, "self": 0.00016580501687712967, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006675479817204177, "count": 8, "is_parallel": true, "self": 0.0006675479817204177 } } } } } } }, "UnityEnvironment.step": { "total": 3046.7987860535795, "count": 337462, "is_parallel": true, "self": 91.16137181149679, "children": { "UnityEnvironment._generate_step_input": { "total": 55.69692347428645, "count": 337462, "is_parallel": true, "self": 55.69692347428645 }, "communicator.exchange": { "total": 2636.7331124062475, "count": 337462, "is_parallel": true, "self": 2636.7331124062475 }, "steps_from_proto": { "total": 263.20737836154876, "count": 674924, "is_parallel": true, "self": 53.35796460311394, "children": { "_process_rank_one_or_two_observation": { "total": 209.84941375843482, "count": 2699696, "is_parallel": true, "self": 209.84941375843482 } } } } }, "steps_from_proto": { "total": 0.02066474812454544, "count": 48, "is_parallel": true, "self": 0.004143711121287197, "children": { "_process_rank_one_or_two_observation": { "total": 0.016521037003258243, "count": 192, "is_parallel": true, "self": 0.016521037003258243 } } } } } } } } }, "trainer_advance": { "total": 1341.0843094842567, "count": 337463, "self": 34.624584180273814, "children": { "process_trajectory": { "total": 716.5783792209695, "count": 337463, "self": 715.0638060080237, "children": { "RLTrainer._checkpoint": { "total": 1.5145732129458338, "count": 10, "self": 1.5145732129458338 } } }, "_update_policy": { "total": 589.8813460830133, "count": 239, "self": 281.5630636715505, "children": { "TorchPOCAOptimizer.update": { "total": 308.31828241146286, "count": 7173, "self": 308.31828241146286 } } } } } } }, "trainer_threads": { "total": 5.089968908578157e-07, "count": 1, "self": 5.089968908578157e-07 }, "TrainerController._save_models": { "total": 0.15709480497753248, "count": 1, "self": 0.0010290969803463668, "children": { "RLTrainer._checkpoint": { "total": 0.1560657079971861, "count": 1, "self": 0.1560657079971861 } } } } } } }