{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.0485711097717285, "min": 2.0096960067749023, "max": 3.295670509338379, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40512.54296875, "min": 22345.341796875, "max": 117245.546875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 53.130434782608695, "min": 46.31132075471698, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19552.0, "min": 13488.0, "max": 26280.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1603.4641878651487, "min": 1183.89241046223, "max": 1611.9522980967179, "count": 478 }, "SoccerTwos.Self-play.ELO.sum": { "value": 295037.41056718735, "min": 2368.4239366025095, "max": 331993.47975224745, "count": 478 }, "SoccerTwos.Step.mean": { "value": 4999994.0, "min": 9632.0, "max": 4999994.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999994.0, "min": 9632.0, "max": 4999994.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.018234437331557274, "min": -0.1353471726179123, "max": 0.21857284009456635, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.3551363945007324, "min": -19.21929931640625, "max": 27.321605682373047, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01912573166191578, "min": -0.1435144543647766, "max": 0.2151324301958084, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.519134521484375, "min": -20.379053115844727, "max": 26.89155387878418, "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": -0.10963695723077525, "min": -0.5714285714285714, "max": 0.5921999999121124, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -20.173200130462646, "min": -49.97800004482269, "max": 52.71919992566109, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.10963695723077525, "min": -0.5714285714285714, "max": 0.5921999999121124, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -20.173200130462646, "min": -49.97800004482269, "max": 52.71919992566109, "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": 0.015300305435569801, "min": 0.009983889403035089, "max": 0.023893511632923036, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015300305435569801, "min": 0.009983889403035089, "max": 0.023893511632923036, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10630333895484606, "min": 5.166237686656435e-06, "max": 0.11564212689797083, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10630333895484606, "min": 5.166237686656435e-06, "max": 0.11564212689797083, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10747923279802005, "min": 5.727423391969447e-06, "max": 0.11835149203737577, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10747923279802005, "min": 5.727423391969447e-06, "max": 0.11835149203737577, "count": 239 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1723392168", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\oooka\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "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": "1.26.4", "end_time_seconds": "1723402079" }, "total": 9910.934570000041, "count": 1, "self": 0.24824730027467012, "children": { "run_training.setup": { "total": 0.13672429998405278, "count": 1, "self": 0.13672429998405278 }, "TrainerController.start_learning": { "total": 9910.549598399783, "count": 1, "self": 7.506645122077316, "children": { "TrainerController._reset_env": { "total": 5.8953447008971125, "count": 25, "self": 5.8953447008971125 }, "TrainerController.advance": { "total": 9896.9692063767, "count": 338399, "self": 6.461926730582491, "children": { "env_step": { "total": 7330.1945369967725, "count": 338399, "self": 4335.045731663471, "children": { "SubprocessEnvManager._take_step": { "total": 2990.569579374045, "count": 338399, "self": 43.23830114072189, "children": { "TorchPolicy.evaluate": { "total": 2947.3312782333232, "count": 633978, "self": 2947.3312782333232 } } }, "workers": { "total": 4.579225959256291, "count": 338399, "self": 0.0, "children": { "worker_root": { "total": 9895.991913326317, "count": 338399, "is_parallel": true, "self": 6460.7014326925855, "children": { "steps_from_proto": { "total": 0.04588100081309676, "count": 50, "is_parallel": true, "self": 0.0076262010261416435, "children": { "_process_rank_one_or_two_observation": { "total": 0.03825479978695512, "count": 200, "is_parallel": true, "self": 0.03825479978695512 } } }, "UnityEnvironment.step": { "total": 3435.244599632919, "count": 338399, "is_parallel": true, "self": 168.21028075320646, "children": { "UnityEnvironment._generate_step_input": { "total": 141.06665501440875, "count": 338399, "is_parallel": true, "self": 141.06665501440875 }, "communicator.exchange": { "total": 2533.740279228892, "count": 338399, "is_parallel": true, "self": 2533.740279228892 }, "steps_from_proto": { "total": 592.2273846364114, "count": 676798, "is_parallel": true, "self": 100.4645481184125, "children": { "_process_rank_one_or_two_observation": { "total": 491.76283651799895, "count": 2707192, "is_parallel": true, "self": 491.76283651799895 } } } } } } } } } } }, "trainer_advance": { "total": 2560.3127426493447, "count": 338399, "self": 57.29812220367603, "children": { "process_trajectory": { "total": 1202.7426054454409, "count": 338399, "self": 1201.0307818448637, "children": { "RLTrainer._checkpoint": { "total": 1.7118236005771905, "count": 10, "self": 1.7118236005771905 } } }, "_update_policy": { "total": 1300.2720150002278, "count": 239, "self": 838.4231178008486, "children": { "TorchPOCAOptimizer.update": { "total": 461.8488971993793, "count": 7173, "self": 461.8488971993793 } } } } } } }, "trainer_threads": { "total": 9.0012326836586e-07, "count": 1, "self": 9.0012326836586e-07 }, "TrainerController._save_models": { "total": 0.17840129998512566, "count": 1, "self": 0.00241199997253716, "children": { "RLTrainer._checkpoint": { "total": 0.1759893000125885, "count": 1, "self": 0.1759893000125885 } } } } } } }