{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8788739442825317, "min": 1.859342098236084, "max": 3.295733690261841, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38419.21484375, "min": 19198.49609375, "max": 122988.6015625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 46.72380952380952, "min": 37.45454545454545, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19624.0, "min": 11732.0, "max": 28432.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1527.7466849923023, "min": 1198.381884011967, "max": 1541.5281000652242, "count": 493 }, "SoccerTwos.Self-play.ELO.sum": { "value": 320826.8038483835, "min": 2397.7696730553207, "max": 391418.11339582165, "count": 493 }, "SoccerTwos.Step.mean": { "value": 4999990.0, "min": 9234.0, "max": 4999990.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999990.0, "min": 9234.0, "max": 4999990.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.014548965729773045, "min": -0.11355549097061157, "max": 0.12140637636184692, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.0552828311920166, "min": -18.736656188964844, "max": 24.207279205322266, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.018708515912294388, "min": -0.10854761302471161, "max": 0.12082657963037491, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.928788185119629, "min": -19.228391647338867, "max": 24.070056915283203, "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": -0.09648761919566563, "min": -0.8571428571428571, "max": 0.4142799973487854, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -20.262400031089783, "min": -53.94899970293045, "max": 55.41799968481064, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09648761919566563, "min": -0.8571428571428571, "max": 0.4142799973487854, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -20.262400031089783, "min": -53.94899970293045, "max": 55.41799968481064, "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": 0.023807371839817886, "min": 0.011235585863081118, "max": 0.024091893970035017, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.023807371839817886, "min": 0.011235585863081118, "max": 0.024091893970035017, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.12161374737819036, "min": 0.0005871520397098114, "max": 0.12445266743501028, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.12161374737819036, "min": 0.0005871520397098114, "max": 0.12445266743501028, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1240325224896272, "min": 0.0005879144640251374, "max": 0.1270775025089582, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1240325224896272, "min": 0.0005879144640251374, "max": 0.1270775025089582, "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": 0.20000000000000007, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679569758", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "D:\\Users\\Magda\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn E:\\rl\\hugging face\\ml-agents\\config\\poca\\SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos4 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1679597990" }, "total": 28232.6846601, "count": 1, "self": 1.3736313000008522, "children": { "run_training.setup": { "total": 0.3744911999999996, "count": 1, "self": 0.3744911999999996 }, "TrainerController.start_learning": { "total": 28230.9365376, "count": 1, "self": 13.695458698955917, "children": { "TrainerController._reset_env": { "total": 11.329685299996584, "count": 25, "self": 11.329685299996584 }, "TrainerController.advance": { "total": 28205.69754380105, "count": 339151, "self": 14.692688699880819, "children": { "env_step": { "total": 9943.589301201071, "count": 339151, "self": 7676.413731701587, "children": { "SubprocessEnvManager._take_step": { "total": 2258.1367367995367, "count": 339151, "self": 84.50295989944334, "children": { "TorchPolicy.evaluate": { "total": 2173.6337769000934, "count": 633374, "self": 2173.6337769000934 } } }, "workers": { "total": 9.038832699948369, "count": 339151, "self": 0.0, "children": { "worker_root": { "total": 28201.778550499606, "count": 339151, "is_parallel": true, "self": 22114.232862199453, "children": { "steps_from_proto": { "total": 0.0745389999995858, "count": 50, "is_parallel": true, "self": 0.014894299997232352, "children": { "_process_rank_one_or_two_observation": { "total": 0.059644700002353446, "count": 200, "is_parallel": true, "self": 0.059644700002353446 } } }, "UnityEnvironment.step": { "total": 6087.471149300156, "count": 339151, "is_parallel": true, "self": 316.06978440136936, "children": { "UnityEnvironment._generate_step_input": { "total": 260.6843880997502, "count": 339151, "is_parallel": true, "self": 260.6843880997502 }, "communicator.exchange": { "total": 4482.199074899027, "count": 339151, "is_parallel": true, "self": 4482.199074899027 }, "steps_from_proto": { "total": 1028.5179019000088, "count": 678302, "is_parallel": true, "self": 215.77275640098503, "children": { "_process_rank_one_or_two_observation": { "total": 812.7451454990238, "count": 2713208, "is_parallel": true, "self": 812.7451454990238 } } } } } } } } } } }, "trainer_advance": { "total": 18247.415553900097, "count": 339151, "self": 98.79165410008136, "children": { "process_trajectory": { "total": 6561.339628700031, "count": 339151, "self": 6558.893376000026, "children": { "RLTrainer._checkpoint": { "total": 2.4462527000050613, "count": 10, "self": 2.4462527000050613 } } }, "_update_policy": { "total": 11587.284271099983, "count": 239, "self": 1112.4320147000471, "children": { "TorchPOCAOptimizer.update": { "total": 10474.852256399936, "count": 7170, "self": 10474.852256399936 } } } } } } }, "trainer_threads": { "total": 2.5000008463393897e-06, "count": 1, "self": 2.5000008463393897e-06 }, "TrainerController._save_models": { "total": 0.2138472999977239, "count": 1, "self": 0.01240259999758564, "children": { "RLTrainer._checkpoint": { "total": 0.20144470000013825, "count": 1, "self": 0.20144470000013825 } } } } } } }