{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5536229610443115, "min": 1.4646261930465698, "max": 1.760551929473877, "count": 2500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33110.8125, "min": 25699.720703125, "max": 40227.5234375, "count": 2500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 59.1566265060241, "min": 39.65040650406504, "max": 107.93617021276596, "count": 2500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19640.0, "min": 17956.0, "max": 21688.0, "count": 2500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1750.8003723371896, "min": 1593.0087183635371, "max": 1780.794708391531, "count": 2500 }, "SoccerTwos.Self-play.ELO.sum": { "value": 290632.8618079735, "min": 146310.62343439288, "max": 420852.7818264838, "count": 2500 }, "SoccerTwos.Step.mean": { "value": 39999991.0, "min": 15009990.0, "max": 39999991.0, "count": 2500 }, "SoccerTwos.Step.sum": { "value": 39999991.0, "min": 15009990.0, "max": 39999991.0, "count": 2500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.008870936930179596, "min": -0.1474827378988266, "max": 0.09885743260383606, "count": 2500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.4725755453109741, "min": -27.809024810791016, "max": 19.67262840270996, "count": 2500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.007196516264230013, "min": -0.14821502566337585, "max": 0.09854020178318024, "count": 2500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.1946216821670532, "min": -28.603038787841797, "max": 19.609500885009766, "count": 2500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.15708433791815515, "min": -0.41191186440193045, "max": 0.3659299303145304, "count": 2500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 26.076000094413757, "min": -60.09400010108948, "max": 53.531400203704834, "count": 2500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.15708433791815515, "min": -0.41191186440193045, "max": 0.3659299303145304, "count": 2500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 26.076000094413757, "min": -60.09400010108948, "max": 53.531400203704834, "count": 2500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02259683023633746, "min": 0.009940433162652577, "max": 0.02742672897487258, "count": 1213 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02259683023633746, "min": 0.009940433162652577, "max": 0.02742672897487258, "count": 1213 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09963143567244212, "min": 0.06914763388534387, "max": 0.12024639075001081, "count": 1213 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09963143567244212, "min": 0.06914763388534387, "max": 0.12024639075001081, "count": 1213 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1010699396332105, "min": 0.06972433105111123, "max": 0.12211980223655701, "count": 1213 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1010699396332105, "min": 0.06972433105111123, "max": 0.12211980223655701, "count": 1213 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1213 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1213 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1213 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1213 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1213 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1213 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684790941", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]", "command_line_arguments": "ml-agents/mlagents/trainers/learn.py ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device=cuda", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1684811384" }, "total": 20443.025759655, "count": 1, "self": 10.002160001997254, "children": { "run_training.setup": { "total": 0.006411153997760266, "count": 1, "self": 0.006411153997760266 }, "TrainerController.start_learning": { "total": 20433.017188499005, "count": 1, "self": 25.589395618218987, "children": { "TrainerController._reset_env": { "total": 2.607153018034296, "count": 126, "self": 2.607153018034296 }, "TrainerController.advance": { "total": 20404.732021175754, "count": 1724500, "self": 24.108064133695734, "children": { "env_step": { "total": 16088.52694243619, "count": 1724500, "self": 12762.514835455564, "children": { "SubprocessEnvManager._take_step": { "total": 3311.9066072354035, "count": 1724500, "self": 128.34764140984043, "children": { "TorchPolicy.evaluate": { "total": 3183.558965825563, "count": 3138322, "self": 3183.558965825563 } } }, "workers": { "total": 14.105499745222914, "count": 1724500, "self": 0.0, "children": { "worker_root": { "total": 20393.824758301052, "count": 1724500, "is_parallel": true, "self": 9818.275900024593, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016739630009396933, "count": 2, "is_parallel": true, "self": 0.00043142000504303724, "children": { "_process_rank_one_or_two_observation": { "total": 0.001242542995896656, "count": 8, "is_parallel": true, "self": 0.001242542995896656 } } }, "UnityEnvironment.step": { "total": 0.017040332000760827, "count": 1, "is_parallel": true, "self": 0.00039519099664175883, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000521194000612013, "count": 1, "is_parallel": true, "self": 0.000521194000612013 }, "communicator.exchange": { "total": 0.014854239001579117, "count": 1, "is_parallel": true, "self": 0.014854239001579117 }, "steps_from_proto": { "total": 0.0012697080019279383, "count": 2, "is_parallel": true, "self": 0.0002921249979408458, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009775830039870925, "count": 8, "is_parallel": true, "self": 0.0009775830039870925 } } } } } } }, "steps_from_proto": { "total": 0.13475248996110167, "count": 250, "is_parallel": true, "self": 0.02830800197989447, "children": { "_process_rank_one_or_two_observation": { "total": 0.1064444879812072, "count": 1000, "is_parallel": true, "self": 0.1064444879812072 } } }, "UnityEnvironment.step": { "total": 10575.414105786498, "count": 1724499, "is_parallel": true, "self": 594.4687469570708, "children": { "UnityEnvironment._generate_step_input": { "total": 533.7888713077118, "count": 1724499, "is_parallel": true, "self": 533.7888713077118 }, "communicator.exchange": { "total": 7700.455723999505, "count": 1724499, "is_parallel": true, "self": 7700.455723999505 }, "steps_from_proto": { "total": 1746.7007635222108, "count": 3448998, "is_parallel": true, "self": 370.921058991873, "children": { "_process_rank_one_or_two_observation": { "total": 1375.7797045303378, "count": 13795992, "is_parallel": true, "self": 1375.7797045303378 } } } } } } } } } } }, "trainer_advance": { "total": 4292.097014605868, "count": 1724500, "self": 171.6146233105028, "children": { "process_trajectory": { "total": 1799.4591496293579, "count": 1724500, "self": 1794.4988771283606, "children": { "RLTrainer._checkpoint": { "total": 4.960272500997235, "count": 50, "self": 4.960272500997235 } } }, "_update_policy": { "total": 2321.0232416660074, "count": 1213, "self": 1566.922360837445, "children": { "TorchPOCAOptimizer.update": { "total": 754.1008808285624, "count": 36390, "self": 754.1008808285624 } } } } } } }, "trainer_threads": { "total": 3.800014383159578e-07, "count": 1, "self": 3.800014383159578e-07 }, "TrainerController._save_models": { "total": 0.08861830699606799, "count": 1, "self": 0.0014972619974287227, "children": { "RLTrainer._checkpoint": { "total": 0.08712104499863926, "count": 1, "self": 0.08712104499863926 } } } } } } }