{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.182844638824463, "min": 3.181525707244873, "max": 3.2957041263580322, "count": 80 }, "SoccerTwos.Policy.Entropy.sum": { "value": 50518.109375, "min": 29227.0078125, "max": 127586.9921875, "count": 80 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 818.1428571428571, "min": 476.0, "max": 999.0, "count": 80 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 22908.0, "min": 16696.0, "max": 23576.0, "count": 80 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1206.8371049762618, "min": 1195.8345822748809, "max": 1206.8371049762618, "count": 66 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4827.348419905047, "min": 2392.1692017894784, "max": 14389.142808817227, "count": 66 }, "SoccerTwos.Step.mean": { "value": 799638.0, "min": 9808.0, "max": 799638.0, "count": 80 }, "SoccerTwos.Step.sum": { "value": 799638.0, "min": 9808.0, "max": 799638.0, "count": 80 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0033227666281163692, "min": -0.02474234253168106, "max": 0.007317614741623402, "count": 80 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.04319596663117409, "min": -0.4924280345439911, "max": 0.1097642183303833, "count": 80 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0036345445550978184, "min": -0.0267522931098938, "max": 0.006356476806104183, "count": 80 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.04724907875061035, "min": -0.5386800169944763, "max": 0.08899067342281342, "count": 80 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 80 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 80 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.2242461511721978, "min": -0.5384615384615384, "max": 0.33637333114941914, "count": 80 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 2.915199965238571, "min": -7.0, "max": 5.045599967241287, "count": 80 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.2242461511721978, "min": -0.5384615384615384, "max": 0.33637333114941914, "count": 80 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 2.915199965238571, "min": -7.0, "max": 5.045599967241287, "count": 80 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 80 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 80 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.022476562972102935, "min": 0.01271723781634743, "max": 0.023505337241416176, "count": 37 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.022476562972102935, "min": 0.01271723781634743, "max": 0.023505337241416176, "count": 37 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.00233484919105346, "min": 9.062712160812226e-06, "max": 0.004905329699007173, "count": 37 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.00233484919105346, "min": 9.062712160812226e-06, "max": 0.004905329699007173, "count": 37 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.002335729360735665, "min": 7.6276505448428605e-06, "max": 0.004691832458289961, "count": 37 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.002335729360735665, "min": 7.6276505448428605e-06, "max": 0.004691832458289961, "count": 37 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 37 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 37 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 37 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 37 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 37 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 37 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682345910", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "G:\\Anaconda\\envs\\Rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos_1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.7.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1682348216" }, "total": 2306.6411957, "count": 1, "self": 0.21903269999984332, "children": { "run_training.setup": { "total": 0.10491850000000014, "count": 1, "self": 0.10491850000000014 }, "TrainerController.start_learning": { "total": 2306.3172445, "count": 1, "self": 1.1632733000010376, "children": { "TrainerController._reset_env": { "total": 5.151768800000344, "count": 5, "self": 5.151768800000344 }, "TrainerController.advance": { "total": 2299.5340294999983, "count": 52189, "self": 1.1959380000098463, "children": { "env_step": { "total": 1062.8713237999702, "count": 52189, "self": 866.2638923999364, "children": { "SubprocessEnvManager._take_step": { "total": 195.85483810001034, "count": 52189, "self": 6.361062900043237, "children": { "TorchPolicy.evaluate": { "total": 189.4937751999671, "count": 103616, "self": 189.4937751999671 } } }, "workers": { "total": 0.7525933000235829, "count": 52188, "self": 0.0, "children": { "worker_root": { "total": 2299.4098572000007, "count": 52188, "is_parallel": true, "self": 1577.947976400028, "children": { "steps_from_proto": { "total": 0.010773600000544725, "count": 10, "is_parallel": true, "self": 0.0023418000004022943, "children": { "_process_rank_one_or_two_observation": { "total": 0.008431800000142431, "count": 40, "is_parallel": true, "self": 0.008431800000142431 } } }, "UnityEnvironment.step": { "total": 721.4511071999723, "count": 52188, "is_parallel": true, "self": 26.85214269995356, "children": { "UnityEnvironment._generate_step_input": { "total": 22.98405239998881, "count": 52188, "is_parallel": true, "self": 22.98405239998881 }, "communicator.exchange": { "total": 587.4680631000268, "count": 52188, "is_parallel": true, "self": 587.4680631000268 }, "steps_from_proto": { "total": 84.14684900000302, "count": 104376, "is_parallel": true, "self": 18.008921700008116, "children": { "_process_rank_one_or_two_observation": { "total": 66.1379272999949, "count": 417504, "is_parallel": true, "self": 66.1379272999949 } } } } } } } } } } }, "trainer_advance": { "total": 1235.4667677000182, "count": 52188, "self": 9.229053200004728, "children": { "process_trajectory": { "total": 165.0186984000129, "count": 52188, "self": 162.9847335000129, "children": { "RLTrainer._checkpoint": { "total": 2.033964900000001, "count": 1, "self": 2.033964900000001 } } }, "_update_policy": { "total": 1061.2190161000005, "count": 37, "self": 130.1017159000046, "children": { "TorchPOCAOptimizer.update": { "total": 931.117300199996, "count": 1110, "self": 931.117300199996 } } } } } } }, "trainer_threads": { "total": 1.100000190490391e-06, "count": 1, "self": 1.100000190490391e-06 }, "TrainerController._save_models": { "total": 0.4681718000001638, "count": 1, "self": 0.029122600000391685, "children": { "RLTrainer._checkpoint": { "total": 0.4390491999997721, "count": 1, "self": 0.4390491999997721 } } } } } } }