{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7588081359863281, "min": 1.6908797025680542, "max": 3.295719861984253, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33825.3984375, "min": 5273.1435546875, "max": 143272.90625, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.93827160493827, "min": 37.59230769230769, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19744.0, "min": 11236.0, "max": 29340.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1561.6993778235915, "min": 1182.9172301275994, "max": 1572.7152468564125, "count": 930 }, "SoccerTwos.Self-play.ELO.sum": { "value": 252995.29920742183, "min": 2365.834460255199, "max": 396588.2787541444, "count": 930 }, "SoccerTwos.Step.mean": { "value": 9999946.0, "min": 9670.0, "max": 9999946.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999946.0, "min": 9670.0, "max": 9999946.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0005929771577939391, "min": -0.10993397235870361, "max": 0.14778369665145874, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.0960623025894165, "min": -19.898048400878906, "max": 25.182292938232422, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.004628224764019251, "min": -0.11462147533893585, "max": 0.1500168740749359, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.7497724294662476, "min": -20.74648666381836, "max": 25.204845428466797, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.016464196605446898, "min": -0.6153846153846154, "max": 0.37161367673140305, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.6671998500823975, "min": -52.334999799728394, "max": 61.50600028038025, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.016464196605446898, "min": -0.6153846153846154, "max": 0.37161367673140305, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.6671998500823975, "min": -52.334999799728394, "max": 61.50600028038025, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01662024947630319, "min": 0.010978754617584248, "max": 0.02382210058373554, "count": 478 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01662024947630319, "min": 0.010978754617584248, "max": 0.02382210058373554, "count": 478 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10861011470357577, "min": 2.6484625664124907e-06, "max": 0.12980319807926813, "count": 478 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10861011470357577, "min": 2.6484625664124907e-06, "max": 0.12980319807926813, "count": 478 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11008004421989123, "min": 2.90544399679978e-06, "max": 0.1320348324875037, "count": 478 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11008004421989123, "min": 2.90544399679978e-06, "max": 0.1320348324875037, "count": 478 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 478 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 478 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 478 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 478 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 478 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 478 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679983956", "python_version": "3.9.16 (main, Mar 8 2023, 04:29:44) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/nagendrak/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos --run-id=SoccerTwos --no-graphics --force", "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": "1680033683" }, "total": 49724.372690283, "count": 1, "self": 0.47004871400713455, "children": { "run_training.setup": { "total": 0.053126408000000014, "count": 1, "self": 0.053126408000000014 }, "TrainerController.start_learning": { "total": 49723.849515161, "count": 1, "self": 18.957341480265313, "children": { "TrainerController._reset_env": { "total": 5.264957535999057, "count": 50, "self": 5.264957535999057 }, "TrainerController.advance": { "total": 49699.35271289774, "count": 679857, "self": 19.628694441627886, "children": { "env_step": { "total": 14516.588156632326, "count": 679857, "self": 11866.56155001186, "children": { "SubprocessEnvManager._take_step": { "total": 2638.729141626691, "count": 679857, "self": 123.66091293688487, "children": { "TorchPolicy.evaluate": { "total": 2515.0682286898063, "count": 1269224, "self": 2515.0682286898063 } } }, "workers": { "total": 11.297464993775279, "count": 679857, "self": 0.0, "children": { "worker_root": { "total": 49685.76442921223, "count": 679857, "is_parallel": true, "self": 40025.68255846995, "children": { "steps_from_proto": { "total": 0.11668987000523767, "count": 100, "is_parallel": true, "self": 0.02464874798996819, "children": { "_process_rank_one_or_two_observation": { "total": 0.09204112201526948, "count": 400, "is_parallel": true, "self": 0.09204112201526948 } } }, "UnityEnvironment.step": { "total": 9659.965180872274, "count": 679857, "is_parallel": true, "self": 544.2142709174022, "children": { "UnityEnvironment._generate_step_input": { "total": 353.90709360012596, "count": 679857, "is_parallel": true, "self": 353.90709360012596 }, "communicator.exchange": { "total": 7078.385508205885, "count": 679857, "is_parallel": true, "self": 7078.385508205885 }, "steps_from_proto": { "total": 1683.4583081488595, "count": 1359714, "is_parallel": true, "self": 355.3363779909266, "children": { "_process_rank_one_or_two_observation": { "total": 1328.1219301579329, "count": 5438856, "is_parallel": true, "self": 1328.1219301579329 } } } } } } } } } } }, "trainer_advance": { "total": 35163.13586182378, "count": 679857, "self": 127.06356120001874, "children": { "process_trajectory": { "total": 4555.459942281793, "count": 679857, "self": 4550.090779544793, "children": { "RLTrainer._checkpoint": { "total": 5.369162737000352, "count": 20, "self": 5.369162737000352 } } }, "_update_policy": { "total": 30480.61235834197, "count": 478, "self": 2022.1009502181769, "children": { "TorchPOCAOptimizer.update": { "total": 28458.51140812379, "count": 14352, "self": 28458.51140812379 } } } } } } }, "trainer_threads": { "total": 1.319996954407543e-06, "count": 1, "self": 1.319996954407543e-06 }, "TrainerController._save_models": { "total": 0.27450192700052867, "count": 1, "self": 0.001933756997459568, "children": { "RLTrainer._checkpoint": { "total": 0.2725681700030691, "count": 1, "self": 0.2725681700030691 } } } } } } }