{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7292009592056274, "min": 1.462592363357544, "max": 1.9122142791748047, "count": 2389 }, "SoccerTwos.Policy.Entropy.sum": { "value": 32979.3203125, "min": 24212.1640625, "max": 44977.6796875, "count": 2389 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 102.63829787234043, "min": 42.309734513274336, "max": 139.72222222222223, "count": 2389 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19296.0, "min": 13632.0, "max": 22212.0, "count": 2389 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1773.3567256010283, "min": 1617.0725424858947, "max": 1795.4278778787505, "count": 2389 }, "SoccerTwos.Self-play.ELO.sum": { "value": 166695.53220649666, "min": 125226.65084387065, "max": 376950.85276496515, "count": 2389 }, "SoccerTwos.Step.mean": { "value": 43909923.0, "min": 20029993.0, "max": 43909923.0, "count": 2389 }, "SoccerTwos.Step.sum": { "value": 43909923.0, "min": 20029993.0, "max": 43909923.0, "count": 2389 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.009478989988565445, "min": -0.14852285385131836, "max": 0.11673429608345032, "count": 2389 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.9005040526390076, "min": -25.079679489135742, "max": 21.479110717773438, "count": 2389 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.009967533871531487, "min": -0.15167224407196045, "max": 0.11416789889335632, "count": 2389 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.9469156861305237, "min": -25.048236846923828, "max": 21.006893157958984, "count": 2389 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2389 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2389 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.06214105392757215, "min": -0.5649581412936366, "max": 0.37623200098673504, "count": 2389 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 5.903400123119354, "min": -52.10960030555725, "max": 46.715599715709686, "count": 2389 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.06214105392757215, "min": -0.5649581412936366, "max": 0.37623200098673504, "count": 2389 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 5.903400123119354, "min": -52.10960030555725, "max": 46.715599715709686, "count": 2389 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2389 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2389 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.011882203624638047, "min": 0.009582694871157097, "max": 0.025316592298137645, "count": 1157 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.011882203624638047, "min": 0.009582694871157097, "max": 0.025316592298137645, "count": 1157 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.05936191206177076, "min": 0.0520331592609485, "max": 0.10736505687236786, "count": 1157 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.05936191206177076, "min": 0.0520331592609485, "max": 0.10736505687236786, "count": 1157 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.060426203658183415, "min": 0.05302219477792581, "max": 0.1105509507159392, "count": 1157 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.060426203658183415, "min": 0.05302219477792581, "max": 0.1105509507159392, "count": 1157 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1157 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1157 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1157 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1157 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1157 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1157 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682488967", "python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\SumitKumar\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --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": "2.0.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1682577625" }, "total": 88657.10877179999, "count": 1, "self": 0.6466955999931088, "children": { "run_training.setup": { "total": 0.13439030000000063, "count": 1, "self": 0.13439030000000063 }, "TrainerController.start_learning": { "total": 88656.3276859, "count": 1, "self": 40.38162810729409, "children": { "TrainerController._reset_env": { "total": 10.351562699999793, "count": 121, "self": 10.351562699999793 }, "TrainerController.advance": { "total": 88605.45012049271, "count": 1626185, "self": 42.31402209843509, "children": { "env_step": { "total": 30901.341653594754, "count": 1626185, "self": 24602.034125704395, "children": { "SubprocessEnvManager._take_step": { "total": 6272.920908495419, "count": 1626185, "self": 233.33606959882127, "children": { "TorchPolicy.evaluate": { "total": 6039.584838896598, "count": 3002014, "self": 6039.584838896598 } } }, "workers": { "total": 26.38661939494063, "count": 1626185, "self": 0.0, "children": { "worker_root": { "total": 88590.45495870047, "count": 1626185, "is_parallel": true, "self": 68627.12687850854, "children": { "steps_from_proto": { "total": 0.21946370000977833, "count": 242, "is_parallel": true, "self": 0.045298800097980596, "children": { "_process_rank_one_or_two_observation": { "total": 0.17416489991179773, "count": 968, "is_parallel": true, "self": 0.17416489991179773 } } }, "UnityEnvironment.step": { "total": 19963.10861649192, "count": 1626185, "is_parallel": true, "self": 969.795710319755, "children": { "UnityEnvironment._generate_step_input": { "total": 787.5773938907478, "count": 1626185, "is_parallel": true, "self": 787.5773938907478 }, "communicator.exchange": { "total": 14964.337375297779, "count": 1626185, "is_parallel": true, "self": 14964.337375297779 }, "steps_from_proto": { "total": 3241.398136983641, "count": 3252370, "is_parallel": true, "self": 654.2783290811499, "children": { "_process_rank_one_or_two_observation": { "total": 2587.119807902491, "count": 13009480, "is_parallel": true, "self": 2587.119807902491 } } } } } } } } } } }, "trainer_advance": { "total": 57661.79444479952, "count": 1626185, "self": 283.05351100598637, "children": { "process_trajectory": { "total": 6362.327779193618, "count": 1626185, "self": 6355.648980993604, "children": { "RLTrainer._checkpoint": { "total": 6.678798200014398, "count": 47, "self": 6.678798200014398 } } }, "_update_policy": { "total": 51016.41315459991, "count": 1158, "self": 3618.5224110005365, "children": { "TorchPOCAOptimizer.update": { "total": 47397.890743599375, "count": 34740, "self": 47397.890743599375 } } } } } } }, "trainer_threads": { "total": 1.4999968698248267e-06, "count": 1, "self": 1.4999968698248267e-06 }, "TrainerController._save_models": { "total": 0.14437310000357684, "count": 1, "self": 0.010778399999253452, "children": { "RLTrainer._checkpoint": { "total": 0.13359470000432339, "count": 1, "self": 0.13359470000432339 } } } } } } }