{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 0.7527447938919067, "min": 0.7313677072525024, "max": 1.1261794567108154, "count": 2798 }, "SoccerTwos.Policy.Entropy.sum": { "value": 16235.19921875, "min": 9298.9775390625, "max": 49444.2265625, "count": 2798 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 94.56363636363636, "min": 32.68027210884354, "max": 111.71111111111111, "count": 2798 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20804.0, "min": 15640.0, "max": 22116.0, "count": 2798 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1400.663939849299, "min": 1343.234013535249, "max": 1449.6001361353983, "count": 2798 }, "SoccerTwos.Self-play.ELO.sum": { "value": 154073.03338342288, "min": 126805.143041464, "max": 411132.5810677633, "count": 2798 }, "SoccerTwos.Step.mean": { "value": 99999958.0, "min": 72029953.0, "max": 99999958.0, "count": 2798 }, "SoccerTwos.Step.sum": { "value": 99999958.0, "min": 72029953.0, "max": 99999958.0, "count": 2798 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.004223335534334183, "min": -0.11730516701936722, "max": 0.049747075885534286, "count": 2798 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.45612025260925293, "min": -27.16960906982422, "max": 11.099370956420898, "count": 2798 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.004822712391614914, "min": -0.11837155371904373, "max": 0.04958106949925423, "count": 2798 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.5208529233932495, "min": -27.064889907836914, "max": 11.35406494140625, "count": 2798 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2798 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2798 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.2900277762501328, "min": -0.42298035642930437, "max": 0.3460653859835405, "count": 2798 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 31.322999835014343, "min": -63.39960038661957, "max": 43.89800024032593, "count": 2798 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.2900277762501328, "min": -0.42298035642930437, "max": 0.3460653859835405, "count": 2798 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 31.322999835014343, "min": -63.39960038661957, "max": 43.89800024032593, "count": 2798 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2798 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2798 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013111631310312077, "min": 0.007057794004989167, "max": 0.017851967857374498, "count": 680 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013111631310312077, "min": 0.007057794004989167, "max": 0.017851967857374498, "count": 680 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09178730522592862, "min": 0.07855677058299383, "max": 0.10971007843812307, "count": 680 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09178730522592862, "min": 0.07855677058299383, "max": 0.10971007843812307, "count": 680 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09236818452676138, "min": 0.07896297425031662, "max": 0.11027897596359253, "count": 680 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09236818452676138, "min": 0.07896297425031662, "max": 0.11027897596359253, "count": 680 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 4.4967996261031204e-08, "min": 4.4967996261031204e-08, "max": 0.00033524322006307094, "count": 680 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 4.4967996261031204e-08, "min": 4.4967996261031204e-08, "max": 0.00033524322006307094, "count": 680 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10000373899999998, "min": 0.10000373899999998, "max": 0.12793692900000003, "count": 680 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10000373899999998, "min": 0.10000373899999998, "max": 0.12793692900000003, "count": 680 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.0186576100000135e-05, "min": 1.0186576100000135e-05, "max": 0.0014040527570999995, "count": 680 }, "SoccerTwos.Policy.Beta.sum": { "value": 1.0186576100000135e-05, "min": 1.0186576100000135e-05, "max": 0.0014040527570999995, "count": 680 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676759098", "python_version": "3.9.0 (default, Nov 15 2020, 14:28:56) \n[GCC 7.3.0]", "command_line_arguments": "/home/olav/dev/anaconda3/envs/rl/bin/mlagents-learn 2x.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=2x --no-graphics --results-dir=./results --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.21.2", "end_time_seconds": "1676775423" }, "total": 16325.73590417899, "count": 1, "self": 0.2780328399967402, "children": { "run_training.setup": { "total": 0.03004099801182747, "count": 1, "self": 0.03004099801182747 }, "TrainerController.start_learning": { "total": 16325.427830340981, "count": 1, "self": 7.091412148496602, "children": { "TrainerController._reset_env": { "total": 19.600715613400098, "count": 141, "self": 19.600715613400098 }, "TrainerController.advance": { "total": 16298.605216769094, "count": 220262, "self": 4.137662488908973, "children": { "env_step": { "total": 8880.398493857821, "count": 220262, "self": 3167.0081850614515, "children": { "SubprocessEnvManager._take_step": { "total": 5704.244866189139, "count": 2014183, "self": 148.02886377077084, "children": { "TorchPolicy.evaluate": { "total": 5556.216002418369, "count": 3718026, "self": 5556.216002418369 } } }, "workers": { "total": 9.145442607230507, "count": 220262, "self": 0.0, "children": { "worker_root": { "total": 195771.2345217719, "count": 2013804, "is_parallel": true, "self": 181232.04467304505, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.012207866937387735, "count": 14, "is_parallel": true, "self": 0.003013705078046769, "children": { "_process_rank_one_or_two_observation": { "total": 0.009194161859340966, "count": 56, "is_parallel": true, "self": 0.009194161859340966 } } }, "UnityEnvironment.step": { "total": 0.10618874401552603, "count": 7, "is_parallel": true, "self": 0.002918574959039688, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0024377889349125326, "count": 7, "is_parallel": true, "self": 0.0024377889349125326 }, "communicator.exchange": { "total": 0.09188617300242186, "count": 7, "is_parallel": true, "self": 0.09188617300242186 }, "steps_from_proto": { "total": 0.00894620711915195, "count": 14, "is_parallel": true, "self": 0.0018873143708333373, "children": { "_process_rank_one_or_two_observation": { "total": 0.007058892748318613, "count": 56, "is_parallel": true, "self": 0.007058892748318613 } } } } } } }, "steps_from_proto": { "total": 3.0666982491966337, "count": 3360, "is_parallel": true, "self": 0.5372369070537388, "children": { "_process_rank_one_or_two_observation": { "total": 2.529461342142895, "count": 13440, "is_parallel": true, "self": 2.529461342142895 } } }, "UnityEnvironment.step": { "total": 14536.123150477652, "count": 2013797, "is_parallel": true, "self": 914.1332000488765, "children": { "UnityEnvironment._generate_step_input": { "total": 607.0277173338691, "count": 2013797, "is_parallel": true, "self": 607.0277173338691 }, "communicator.exchange": { "total": 10221.373080469086, "count": 2013797, "is_parallel": true, "self": 10221.373080469086 }, "steps_from_proto": { "total": 2793.58915262582, "count": 4027594, "is_parallel": true, "self": 538.6196256728144, "children": { "_process_rank_one_or_two_observation": { "total": 2254.9695269530057, "count": 16110376, "is_parallel": true, "self": 2254.9695269530057 } } } } } } } } } } }, "trainer_advance": { "total": 7414.069060422364, "count": 220262, "self": 162.93663687229855, "children": { "process_trajectory": { "total": 2979.520096707449, "count": 220262, "self": 2972.5634005694883, "children": { "RLTrainer._checkpoint": { "total": 6.9566961379605345, "count": 56, "self": 6.9566961379605345 } } }, "_update_policy": { "total": 4271.612326842616, "count": 680, "self": 3076.523804622295, "children": { "TorchPOCAOptimizer.update": { "total": 1195.0885222203215, "count": 20400, "self": 1195.0885222203215 } } } } } } }, "trainer_threads": { "total": 7.600174285471439e-07, "count": 1, "self": 7.600174285471439e-07 }, "TrainerController._save_models": { "total": 0.13048504997277632, "count": 1, "self": 0.0009444899624213576, "children": { "RLTrainer._checkpoint": { "total": 0.12954056001035497, "count": 1, "self": 0.12954056001035497 } } } } } } }