{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3727142810821533, "min": 1.2437572479248047, "max": 3.295734405517578, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28596.3828125, "min": 22264.66796875, "max": 107133.75, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 66.30666666666667, "min": 37.0, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19892.0, "min": 12992.0, "max": 28660.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1574.3835743127636, "min": 1199.5028730369677, "max": 1696.6728846329497, "count": 4997 }, "SoccerTwos.Self-play.ELO.sum": { "value": 236157.53614691453, "min": 2405.345543435026, "max": 423531.84905092954, "count": 4997 }, "SoccerTwos.Step.mean": { "value": 49999972.0, "min": 9346.0, "max": 49999972.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999972.0, "min": 9346.0, "max": 49999972.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.030712326988577843, "min": -0.14744554460048676, "max": 0.24148403108119965, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.637561321258545, "min": -29.240467071533203, "max": 30.185503005981445, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.030260281637310982, "min": -0.14783990383148193, "max": 0.23918989300727844, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.569302558898926, "min": -29.56571388244629, "max": 30.165523529052734, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.02762119501631781, "min": -0.5714285714285714, "max": 0.5549624990671873, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.170800447463989, "min": -67.42159986495972, "max": 63.35360026359558, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.02762119501631781, "min": -0.5714285714285714, "max": 0.5549624990671873, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.170800447463989, "min": -67.42159986495972, "max": 63.35360026359558, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014172838624411573, "min": 0.010058914470331122, "max": 0.028468370631647606, "count": 2427 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014172838624411573, "min": 0.010058914470331122, "max": 0.028468370631647606, "count": 2427 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09486279909809431, "min": 0.00048418187701220936, "max": 0.1365848071873188, "count": 2427 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09486279909809431, "min": 0.00048418187701220936, "max": 0.1365848071873188, "count": 2427 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09588683173060417, "min": 0.0004805245218449272, "max": 0.13937359750270845, "count": 2427 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09588683173060417, "min": 0.0004805245218449272, "max": 0.13937359750270845, "count": 2427 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2427 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2427 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2427 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2427 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2427 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2427 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1724187716", "python_version": "3.10.12 (main, Jul 5 2023, 15:02:25) [Clang 14.0.6 ]", "command_line_arguments": "/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0", "numpy_version": "1.23.5", "end_time_seconds": "1724372224" }, "total": 184500.975800833, "count": 1, "self": 0.34230149901122786, "children": { "run_training.setup": { "total": 0.028737208995153196, "count": 1, "self": 0.028737208995153196 }, "TrainerController.start_learning": { "total": 184500.604762125, "count": 1, "self": 39.55321783575346, "children": { "TrainerController._reset_env": { "total": 13.779861952032661, "count": 250, "self": 13.779861952032661 }, "TrainerController.advance": { "total": 184447.16995412923, "count": 3466643, "self": 34.237620061816415, "children": { "env_step": { "total": 144781.6001774151, "count": 3466643, "self": 139104.27306577418, "children": { "SubprocessEnvManager._take_step": { "total": 5652.818099025244, "count": 3466643, "self": 167.408983593632, "children": { "TorchPolicy.evaluate": { "total": 5485.409115431612, "count": 6276628, "self": 5485.409115431612 } } }, "workers": { "total": 24.509012615686515, "count": 3466643, "self": 0.0, "children": { "worker_root": { "total": 184435.6914086728, "count": 3466643, "is_parallel": true, "self": 49738.526523255015, "children": { "steps_from_proto": { "total": 0.3814245441026287, "count": 500, "is_parallel": true, "self": 0.0419856928056106, "children": { "_process_rank_one_or_two_observation": { "total": 0.3394388512970181, "count": 2000, "is_parallel": true, "self": 0.3394388512970181 } } }, "UnityEnvironment.step": { "total": 134696.78346087367, "count": 3466643, "is_parallel": true, "self": 398.35641566760023, "children": { "UnityEnvironment._generate_step_input": { "total": 2519.8526080568263, "count": 3466643, "is_parallel": true, "self": 2519.8526080568263 }, "communicator.exchange": { "total": 126788.58995363538, "count": 3466643, "is_parallel": true, "self": 126788.58995363538 }, "steps_from_proto": { "total": 4989.984483513879, "count": 6933286, "is_parallel": true, "self": 563.9382228220202, "children": { "_process_rank_one_or_two_observation": { "total": 4426.046260691859, "count": 27733144, "is_parallel": true, "self": 4426.046260691859 } } } } } } } } } } }, "trainer_advance": { "total": 39631.33215665232, "count": 3466643, "self": 322.57620075775776, "children": { "process_trajectory": { "total": 7475.644205916935, "count": 3466643, "self": 7463.305086040811, "children": { "RLTrainer._checkpoint": { "total": 12.339119876123732, "count": 100, "self": 12.339119876123732 } } }, "_update_policy": { "total": 31833.11174997763, "count": 2427, "self": 3101.9803480033443, "children": { "TorchPOCAOptimizer.update": { "total": 28731.131401974286, "count": 72810, "self": 28731.131401974286 } } } } } } }, "trainer_threads": { "total": 3.7500285543501377e-07, "count": 1, "self": 3.7500285543501377e-07 }, "TrainerController._save_models": { "total": 0.10172783298185095, "count": 1, "self": 0.0017986239690799266, "children": { "RLTrainer._checkpoint": { "total": 0.09992920901277103, "count": 1, "self": 0.09992920901277103 } } } } } } }