{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.0753798484802246, "min": 1.6941413879394531, "max": 2.123616933822632, "count": 432 }, "SoccerTwos.Policy.Entropy.sum": { "value": 41441.18359375, "min": 13059.85546875, "max": 48303.5234375, "count": 432 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.76744186046512, "min": 45.5607476635514, "max": 85.29310344827586, "count": 432 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19872.0, "min": 5992.0, "max": 21172.0, "count": 432 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1562.370385379922, "min": 1478.0449380077948, "max": 1571.2183482850123, "count": 432 }, "SoccerTwos.Self-play.ELO.sum": { "value": 268727.7062853466, "min": 85712.8576546484, "max": 331772.55834787374, "count": 432 }, "SoccerTwos.Step.mean": { "value": 16049992.0, "min": 11739974.0, "max": 16049992.0, "count": 432 }, "SoccerTwos.Step.sum": { "value": 16049992.0, "min": 11739974.0, "max": 16049992.0, "count": 432 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.011824635788798332, "min": -0.12827473878860474, "max": 0.08283628523349762, "count": 432 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 2.022012710571289, "min": -23.987377166748047, "max": 12.673952102661133, "count": 432 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.011609936133027077, "min": -0.12794987857341766, "max": 0.08335159718990326, "count": 432 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.9852991104125977, "min": -23.92662811279297, "max": 12.75279426574707, "count": 432 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 432 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 432 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.020430409420303434, "min": -0.3276352956014521, "max": 0.31089248374707434, "count": 432 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -3.493600010871887, "min": -63.08319973945618, "max": 53.784399688243866, "count": 432 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.020430409420303434, "min": -0.3276352956014521, "max": 0.31089248374707434, "count": 432 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -3.493600010871887, "min": -63.08319973945618, "max": 53.784399688243866, "count": 432 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 432 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 432 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.019133638390000367, "min": 0.009504728168637181, "max": 0.024814592476468535, "count": 209 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.019133638390000367, "min": 0.009504728168637181, "max": 0.024814592476468535, "count": 209 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10119041601816813, "min": 0.089591034501791, "max": 0.1190962294737498, "count": 209 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10119041601816813, "min": 0.089591034501791, "max": 0.1190962294737498, "count": 209 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1021848164498806, "min": 0.09043613796432813, "max": 0.12001427635550499, "count": 209 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1021848164498806, "min": 0.09043613796432813, "max": 0.12001427635550499, "count": 209 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 9.999999999999998e-05, "min": 9.999999999999998e-05, "max": 9.999999999999998e-05, "count": 209 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 9.999999999999998e-05, "min": 9.999999999999998e-05, "max": 9.999999999999998e-05, "count": 209 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 209 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 209 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 209 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 209 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1683129627", "python_version": "3.9.0 (default, Nov 15 2020, 14:28:56) \n[GCC 7.3.0]", "command_line_arguments": "/home/vld/anaconda3/envs/hf_rl_course/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume", "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": "1683149722" }, "total": 20095.0709115, "count": 1, "self": 0.14871449999918696, "children": { "run_training.setup": { "total": 0.050549100000353064, "count": 1, "self": 0.050549100000353064 }, "TrainerController.start_learning": { "total": 20094.8716479, "count": 1, "self": 6.860395402669383, "children": { "TrainerController._reset_env": { "total": 10.521520900008909, "count": 23, "self": 10.521520900008909 }, "TrainerController.advance": { "total": 20077.00831859732, "count": 299972, "self": 6.951193199689442, "children": { "env_step": { "total": 14850.574014399841, "count": 299972, "self": 5623.9756530980085, "children": { "SubprocessEnvManager._take_step": { "total": 9222.60552849892, "count": 299972, "self": 41.12715460173058, "children": { "TorchPolicy.evaluate": { "total": 9181.47837389719, "count": 542182, "self": 9181.47837389719 } } }, "workers": { "total": 3.9928328029127442, "count": 299972, "self": 0.0, "children": { "worker_root": { "total": 20073.40502370076, "count": 299972, "is_parallel": true, "self": 15156.218758199837, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003249000001233071, "count": 2, "is_parallel": true, "self": 0.0009197999970638193, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023292000041692518, "count": 8, "is_parallel": true, "self": 0.0023292000041692518 } } }, "UnityEnvironment.step": { "total": 0.04167540000344161, "count": 1, "is_parallel": true, "self": 0.000604000008024741, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005910000036237761, "count": 1, "is_parallel": true, "self": 0.0005910000036237761 }, "communicator.exchange": { "total": 0.038517299995874055, "count": 1, "is_parallel": true, "self": 0.038517299995874055 }, "steps_from_proto": { "total": 0.0019630999959190376, "count": 2, "is_parallel": true, "self": 0.0004978000069968402, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014652999889221974, "count": 8, "is_parallel": true, "self": 0.0014652999889221974 } } } } } } }, "steps_from_proto": { "total": 0.034217100001114886, "count": 44, "is_parallel": true, "self": 0.007301599987840746, "children": { "_process_rank_one_or_two_observation": { "total": 0.02691550001327414, "count": 176, "is_parallel": true, "self": 0.02691550001327414 } } }, "UnityEnvironment.step": { "total": 4917.152048400923, "count": 299971, "is_parallel": true, "self": 154.68728360757814, "children": { "UnityEnvironment._generate_step_input": { "total": 106.43757610006287, "count": 299971, "is_parallel": true, "self": 106.43757610006287 }, "communicator.exchange": { "total": 4179.489904796239, "count": 299971, "is_parallel": true, "self": 4179.489904796239 }, "steps_from_proto": { "total": 476.5372838970434, "count": 599942, "is_parallel": true, "self": 103.17700669672922, "children": { "_process_rank_one_or_two_observation": { "total": 373.36027720031416, "count": 2399768, "is_parallel": true, "self": 373.36027720031416 } } } } } } } } } } }, "trainer_advance": { "total": 5219.4831109977895, "count": 299972, "self": 47.44477459735208, "children": { "process_trajectory": { "total": 3497.633985700464, "count": 299972, "self": 3494.4295499004656, "children": { "RLTrainer._checkpoint": { "total": 3.204435799998464, "count": 9, "self": 3.204435799998464 } } }, "_update_policy": { "total": 1674.4043506999733, "count": 210, "self": 628.5340833001101, "children": { "TorchPOCAOptimizer.update": { "total": 1045.8702673998632, "count": 6292, "self": 1045.8702673998632 } } } } } } }, "trainer_threads": { "total": 1.0000003385357559e-06, "count": 1, "self": 1.0000003385357559e-06 }, "TrainerController._save_models": { "total": 0.4814120000010007, "count": 1, "self": 0.1450870999979088, "children": { "RLTrainer._checkpoint": { "total": 0.3363249000030919, "count": 1, "self": 0.3363249000030919 } } } } } } }