{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7701833248138428, "min": 1.3719481229782104, "max": 1.871724009513855, "count": 821 }, "SoccerTwos.Policy.Entropy.sum": { "value": 48545.5078125, "min": 22207.037109375, "max": 56677.78515625, "count": 821 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 78.80645161290323, "min": 42.93693693693694, "max": 117.11627906976744, "count": 821 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19544.0, "min": 10080.0, "max": 21532.0, "count": 821 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1525.340507142494, "min": 1479.7606759542728, "max": 1655.5722462772112, "count": 821 }, "SoccerTwos.Self-play.ELO.sum": { "value": 189142.22288566927, "min": 127944.68200545188, "max": 361320.466831879, "count": 821 }, "SoccerTwos.Step.mean": { "value": 37899944.0, "min": 29699920.0, "max": 37899944.0, "count": 821 }, "SoccerTwos.Step.sum": { "value": 37899944.0, "min": 29699920.0, "max": 37899944.0, "count": 821 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.058571405708789825, "min": -0.13811704516410828, "max": 0.10500992834568024, "count": 821 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 7.262854099273682, "min": -24.70503807067871, "max": 14.176340103149414, "count": 821 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.05869920179247856, "min": -0.13186343014240265, "max": 0.1037633940577507, "count": 821 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 7.278700828552246, "min": -25.713367462158203, "max": 14.008058547973633, "count": 821 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 821 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 821 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.17129032169618913, "min": -0.40771612749304825, "max": 0.2733866646176293, "count": 821 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 21.239999890327454, "min": -62.76160001754761, "max": 43.67039978504181, "count": 821 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.17129032169618913, "min": -0.40771612749304825, "max": 0.2733866646176293, "count": 821 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 21.239999890327454, "min": -62.76160001754761, "max": 43.67039978504181, "count": 821 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 821 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 821 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02879449994652532, "min": 0.024823492643675612, "max": 0.0333783227474972, "count": 199 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02879449994652532, "min": 0.024823492643675612, "max": 0.0333783227474972, "count": 199 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07804813447097937, "min": 0.06403212292740743, "max": 0.10126510423918565, "count": 199 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07804813447097937, "min": 0.06403212292740743, "max": 0.10126510423918565, "count": 199 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08070893287658691, "min": 0.06631886282314857, "max": 0.10316466639439265, "count": 199 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08070893287658691, "min": 0.06631886282314857, "max": 0.10316466639439265, "count": 199 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.001, "min": 0.001, "max": 0.001, "count": 199 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.001, "min": 0.001, "max": 0.001, "count": 199 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.23000000000000004, "min": 0.23000000000000004, "max": 0.23000000000000004, "count": 199 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.23000000000000004, "min": 0.23000000000000004, "max": 0.23000000000000004, "count": 199 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.006, "min": 0.006, "max": 0.006, "count": 199 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.006, "min": 0.006, "max": 0.006, "count": 199 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1676556934", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\hecto\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=Pires_and_Lundberg --no-graphics --num-envs=3 --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1676579831" }, "total": 22897.0813614, "count": 1, "self": 0.0077146000003267545, "children": { "run_training.setup": { "total": 0.226788, "count": 1, "self": 0.226788 }, "TrainerController.start_learning": { "total": 22896.8468588, "count": 1, "self": 16.652563701100007, "children": { "TrainerController._reset_env": { "total": 15.79089869999327, "count": 328, "self": 15.79089869999327 }, "TrainerController.advance": { "total": 22864.257761498906, "count": 565444, "self": 15.908553398705408, "children": { "env_step": { "total": 3971.9426861001193, "count": 565444, "self": 1417.0439159997322, "children": { "SubprocessEnvManager._take_step": { "total": 2546.786615399115, "count": 624712, "self": 95.58230460170853, "children": { "TorchPolicy.evaluate": { "total": 2451.2043107974064, "count": 1158892, "self": 2451.2043107974064 } } }, "workers": { "total": 8.112154701272292, "count": 565444, "self": 0.0, "children": { "worker_root": { "total": 68241.08778149853, "count": 624258, "is_parallel": true, "self": 61950.040563398084, "children": { "steps_from_proto": { "total": 1.4915279000327608, "count": 1964, "is_parallel": true, "self": 0.30799659997581363, "children": { "_process_rank_one_or_two_observation": { "total": 1.1835313000569472, "count": 7856, "is_parallel": true, "self": 1.1835313000569472 } } }, "UnityEnvironment.step": { "total": 6289.555690200412, "count": 624258, "is_parallel": true, "self": 342.1256913010302, "children": { "UnityEnvironment._generate_step_input": { "total": 265.4663002990906, "count": 624258, "is_parallel": true, "self": 265.4663002990906 }, "communicator.exchange": { "total": 4668.101448000436, "count": 624258, "is_parallel": true, "self": 4668.101448000436 }, "steps_from_proto": { "total": 1013.8622505998544, "count": 1248516, "is_parallel": true, "self": 209.82015870185774, "children": { "_process_rank_one_or_two_observation": { "total": 804.0420918979967, "count": 4994064, "is_parallel": true, "self": 804.0420918979967 } } } } } } } } } } }, "trainer_advance": { "total": 18876.40652200008, "count": 565444, "self": 117.15673470124966, "children": { "process_trajectory": { "total": 2148.756217498842, "count": 565444, "self": 2146.9036823988413, "children": { "RLTrainer._checkpoint": { "total": 1.8525351000007504, "count": 16, "self": 1.8525351000007504 } } }, "_update_policy": { "total": 16610.49356979999, "count": 200, "self": 1185.1533127000675, "children": { "TorchPOCAOptimizer.update": { "total": 15425.340257099922, "count": 11999, "self": 15425.340257099922 } } } } } } }, "trainer_threads": { "total": 1.5000005078036338e-06, "count": 1, "self": 1.5000005078036338e-06 }, "TrainerController._save_models": { "total": 0.14563339999949676, "count": 1, "self": 0.02459169999929145, "children": { "RLTrainer._checkpoint": { "total": 0.12104170000020531, "count": 1, "self": 0.12104170000020531 } } } } } } }