{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.032137155532837, "min": 2.963549852371216, "max": 3.295748472213745, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 39102.44140625, "min": 16359.21484375, "max": 145874.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 372.8, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 12120.0, "max": 28872.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1190.250376742316, "min": 1190.250376742316, "max": 1212.6360633601846, "count": 319 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2380.500753484632, "min": 2380.500753484632, "max": 24094.756005446357, "count": 319 }, "SoccerTwos.Step.mean": { "value": 4999138.0, "min": 9454.0, "max": 4999138.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999138.0, "min": 9454.0, "max": 4999138.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0010223295539617538, "min": -0.030991630628705025, "max": 0.06163818761706352, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.010223295539617538, "min": -0.42233914136886597, "max": 0.9245728254318237, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.00041919006616808474, "min": -0.031949497759342194, "max": 0.05901928246021271, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.0041919006034731865, "min": -0.4212222993373871, "max": 0.767250657081604, "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": 0.0, "min": -0.5333333333333333, "max": 0.2937538532110361, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -9.526000022888184, "max": 3.9664000272750854, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.5333333333333333, "max": 0.2937538532110361, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -9.526000022888184, "max": 3.9664000272750854, "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": 0.012826999464414257, "min": 0.011360754184715915, "max": 0.02327696944994386, "count": 232 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012826999464414257, "min": 0.011360754184715915, "max": 0.02327696944994386, "count": 232 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0008377967720055797, "min": 1.38548439683935e-08, "max": 0.008497005390624205, "count": 232 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0008377967720055797, "min": 1.38548439683935e-08, "max": 0.008497005390624205, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0008388687114347704, "min": 2.501840269767778e-08, "max": 0.008795255158717433, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0008388687114347704, "min": 2.501840269767778e-08, "max": 0.008795255158717433, "count": 232 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 232 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 232 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683080860", "python_version": "3.9.12 (main, Jun 1 2022, 11:38:51) \n[GCC 7.5.0]", "command_line_arguments": "/root/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1683097935" }, "total": 17075.17199491395, "count": 1, "self": 3.8121282688807696, "children": { "run_training.setup": { "total": 0.015761768096126616, "count": 1, "self": 0.015761768096126616 }, "TrainerController.start_learning": { "total": 17071.344104876975, "count": 1, "self": 10.04940227442421, "children": { "TrainerController._reset_env": { "total": 3.8664690089644864, "count": 25, "self": 3.8664690089644864 }, "TrainerController.advance": { "total": 17056.643019690528, "count": 325774, "self": 12.52421457937453, "children": { "env_step": { "total": 8968.410422817105, "count": 325774, "self": 7395.774184651789, "children": { "SubprocessEnvManager._take_step": { "total": 1566.0425518353004, "count": 325774, "self": 73.3744503245689, "children": { "TorchPolicy.evaluate": { "total": 1492.6681015107315, "count": 646946, "self": 1492.6681015107315 } } }, "workers": { "total": 6.593686330015771, "count": 325774, "self": 0.0, "children": { "worker_root": { "total": 17042.374925229116, "count": 325774, "is_parallel": true, "self": 10838.432083601016, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003074040054343641, "count": 2, "is_parallel": true, "self": 0.0009026189800351858, "children": { "_process_rank_one_or_two_observation": { "total": 0.002171421074308455, "count": 8, "is_parallel": true, "self": 0.002171421074308455 } } }, "UnityEnvironment.step": { "total": 0.03266055101994425, "count": 1, "is_parallel": true, "self": 0.0008589179487898946, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005859830416738987, "count": 1, "is_parallel": true, "self": 0.0005859830416738987 }, "communicator.exchange": { "total": 0.028584234067238867, "count": 1, "is_parallel": true, "self": 0.028584234067238867 }, "steps_from_proto": { "total": 0.00263141596224159, "count": 2, "is_parallel": true, "self": 0.0005592990200966597, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020721169421449304, "count": 8, "is_parallel": true, "self": 0.0020721169421449304 } } } } } } }, "UnityEnvironment.step": { "total": 6203.901006862754, "count": 325773, "is_parallel": true, "self": 261.6610836646287, "children": { "UnityEnvironment._generate_step_input": { "total": 194.6982281965902, "count": 325773, "is_parallel": true, "self": 194.6982281965902 }, "communicator.exchange": { "total": 5014.777858937625, "count": 325773, "is_parallel": true, "self": 5014.777858937625 }, "steps_from_proto": { "total": 732.7638360639103, "count": 651546, "is_parallel": true, "self": 155.89200008881744, "children": { "_process_rank_one_or_two_observation": { "total": 576.8718359750928, "count": 2606184, "is_parallel": true, "self": 576.8718359750928 } } } } }, "steps_from_proto": { "total": 0.041834765346720815, "count": 48, "is_parallel": true, "self": 0.008902369649149477, "children": { "_process_rank_one_or_two_observation": { "total": 0.03293239569757134, "count": 192, "is_parallel": true, "self": 0.03293239569757134 } } } } } } } } }, "trainer_advance": { "total": 8075.708382294048, "count": 325774, "self": 76.22807634156197, "children": { "process_trajectory": { "total": 988.2275709247915, "count": 325774, "self": 983.728322971845, "children": { "RLTrainer._checkpoint": { "total": 4.499247952946462, "count": 10, "self": 4.499247952946462 } } }, "_update_policy": { "total": 7011.252735027694, "count": 232, "self": 925.573002877296, "children": { "TorchPOCAOptimizer.update": { "total": 6085.679732150398, "count": 6960, "self": 6085.679732150398 } } } } } } }, "trainer_threads": { "total": 1.3320241123437881e-06, "count": 1, "self": 1.3320241123437881e-06 }, "TrainerController._save_models": { "total": 0.7852125710342079, "count": 1, "self": 0.04559620609506965, "children": { "RLTrainer._checkpoint": { "total": 0.7396163649391383, "count": 1, "self": 0.7396163649391383 } } } } } } }