{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2872161865234375, "min": 3.283947467803955, "max": 3.2958364486694336, "count": 13 }, "SoccerTwos.Policy.Entropy.sum": { "value": 43759.421875, "min": 42781.015625, "max": 105466.765625, "count": 13 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 811.5, "min": 494.7142857142857, "max": 906.6, "count": 13 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19476.0, "min": 13852.0, "max": 27716.0, "count": 13 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1202.1297790220663, "min": 1198.6916415169974, "max": 1202.9673173073832, "count": 13 }, "SoccerTwos.Self-play.ELO.sum": { "value": 7212.778674132397, "min": 4798.067989990133, "max": 14399.635556919653, "count": 13 }, "SoccerTwos.Step.mean": { "value": 129712.0, "min": 9876.0, "max": 129712.0, "count": 13 }, "SoccerTwos.Step.sum": { "value": 129712.0, "min": 9876.0, "max": 129712.0, "count": 13 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0014713257551193237, "min": -0.0014713257551193237, "max": 0.05451347306370735, "count": 13 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.017655909061431885, "min": -0.017655909061431885, "max": 0.8722155690193176, "count": 13 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0014713257551193237, "min": -0.0014713257551193237, "max": 0.05451347306370735, "count": 13 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.017655909061431885, "min": -0.017655909061431885, "max": 0.8722155690193176, "count": 13 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 13 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 13 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.5, "min": -0.5, "max": 0.2147230735191932, "count": 13 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -6.0, "min": -6.0, "max": 2.7913999557495117, "count": 13 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.5, "min": -0.5, "max": 0.2147230735191932, "count": 13 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -6.0, "min": -6.0, "max": 2.7913999557495117, "count": 13 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 13 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 13 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.012890987443582465, "min": 0.00523900882108137, "max": 0.013176202323908608, "count": 5 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.012890987443582465, "min": 0.00523900882108137, "max": 0.013176202323908608, "count": 5 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.001682706782594323, "min": 0.0012276781412462394, "max": 0.003556596456716458, "count": 5 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.001682706782594323, "min": 0.0012276781412462394, "max": 0.003556596456716458, "count": 5 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.001682706782594323, "min": 0.0012276781412462394, "max": 0.003556596456716458, "count": 5 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.001682706782594323, "min": 0.0012276781412462394, "max": 0.003556596456716458, "count": 5 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 5 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 5 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 5 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 5 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 5 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005, "min": 0.005, "max": 0.005, "count": 5 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1703591226", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/cybertron/anaconda3/envs/rl/bin/mlagents-learn /home/cybertron/Desktop/ml-agents/config/poca/SoccerTwos.yaml --env=training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.0.0", "mlagents_envs_version": "1.0.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.1", "numpy_version": "1.21.2", "end_time_seconds": "1703591510" }, "total": 284.3635966809961, "count": 1, "self": 0.21882801299216226, "children": { "run_training.setup": { "total": 0.012106276000849903, "count": 1, "self": 0.012106276000849903 }, "TrainerController.start_learning": { "total": 284.1326623920031, "count": 1, "self": 0.13699659491248894, "children": { "TrainerController._reset_env": { "total": 2.0738567980006337, "count": 1, "self": 2.0738567980006337 }, "TrainerController.advance": { "total": 279.10317788109387, "count": 8577, "self": 0.1445215416897554, "children": { "env_step": { "total": 198.89272247839108, "count": 8577, "self": 100.6482229002795, "children": { "SubprocessEnvManager._take_step": { "total": 98.15602654993563, "count": 8577, "self": 0.9458562079526018, "children": { "TorchPolicy.evaluate": { "total": 97.21017034198303, "count": 17038, "self": 97.21017034198303 } } }, "workers": { "total": 0.08847302817594027, "count": 8577, "self": 0.0, "children": { "worker_root": { "total": 279.9393852657813, "count": 8577, "is_parallel": true, "self": 195.6091849016957, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018885289973695762, "count": 2, "is_parallel": true, "self": 0.0004485460085561499, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014399829888134263, "count": 8, "is_parallel": true, "self": 0.0014399829888134263 } } }, "UnityEnvironment.step": { "total": 0.019859125000948552, "count": 1, "is_parallel": true, "self": 0.00042441000550752506, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0005746079987147823, "count": 1, "is_parallel": true, "self": 0.0005746079987147823 }, "communicator.exchange": { "total": 0.017522023001220077, "count": 1, "is_parallel": true, "self": 0.017522023001220077 }, "steps_from_proto": { "total": 0.0013380839955061674, "count": 2, "is_parallel": true, "self": 0.0002767289915936999, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010613550039124675, "count": 8, "is_parallel": true, "self": 0.0010613550039124675 } } } } } } }, "UnityEnvironment.step": { "total": 84.33020036408561, "count": 8576, "is_parallel": true, "self": 4.363296162802726, "children": { "UnityEnvironment._generate_step_input": { "total": 2.5144244331968366, "count": 8576, "is_parallel": true, "self": 2.5144244331968366 }, "communicator.exchange": { "total": 64.61790556683991, "count": 8576, "is_parallel": true, "self": 64.61790556683991 }, "steps_from_proto": { "total": 12.834574201246141, "count": 17152, "is_parallel": true, "self": 2.373371579713421, "children": { "_process_rank_one_or_two_observation": { "total": 10.46120262153272, "count": 68608, "is_parallel": true, "self": 10.46120262153272 } } } } } } } } } } }, "trainer_advance": { "total": 80.06593386101304, "count": 8577, "self": 1.3821683759160805, "children": { "process_trajectory": { "total": 11.169169155109557, "count": 8577, "self": 11.169169155109557 }, "_update_policy": { "total": 67.5145963299874, "count": 6, "self": 12.408137330006866, "children": { "TorchPOCAOptimizer.update": { "total": 55.10645899998053, "count": 76, "self": 55.10645899998053 } } } } } } }, "TrainerController._save_models": { "total": 2.8186311179961194, "count": 1, "self": 2.9962000553496182e-05, "children": { "RLTrainer._checkpoint": { "total": 2.818601155995566, "count": 1, "self": 2.818601155995566 } } } } } } }