{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4548401832580566, "min": 1.3122400045394897, "max": 3.2957544326782227, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 30214.12109375, "min": 21970.974609375, "max": 114942.1171875, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.164556962025316, "min": 38.76984126984127, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19644.0, "min": 8368.0, "max": 31968.0, "count": 5000 }, "SoccerTwos.Step.mean": { "value": 49999992.0, "min": 9000.0, "max": 49999992.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999992.0, "min": 9000.0, "max": 49999992.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05072049796581268, "min": -0.1604163646697998, "max": 0.17390087246894836, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -8.064558982849121, "min": -31.922855377197266, "max": 32.51946258544922, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05126652121543884, "min": -0.15486522018909454, "max": 0.18436096608638763, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -8.151376724243164, "min": -30.818180084228516, "max": 34.475502014160156, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.0878729557841079, "min": -0.5560210535400792, "max": 0.5212274998426437, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -13.971799969673157, "min": -67.99840021133423, "max": 74.7799996137619, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.0878729557841079, "min": -0.5560210535400792, "max": 0.5212274998426437, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -13.971799969673157, "min": -67.99840021133423, "max": 74.7799996137619, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1548.0452045656339, "min": 1202.5799518752465, "max": 1678.968794999833, "count": 4991 }, "SoccerTwos.Self-play.ELO.sum": { "value": 244591.14232137013, "min": 2409.6249726922138, "max": 397684.41469362855, "count": 4991 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01345443063764833, "min": 0.008745923440437764, "max": 0.024665497057139874, "count": 2425 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01345443063764833, "min": 0.008745923440437764, "max": 0.024665497057139874, "count": 2425 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08849603260556857, "min": 0.00016593868252433216, "max": 0.12422476882735888, "count": 2425 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08849603260556857, "min": 0.00016593868252433216, "max": 0.12422476882735888, "count": 2425 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08994188259045283, "min": 0.00017009946350299288, "max": 0.12701295018196107, "count": 2425 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08994188259045283, "min": 0.00017009946350299288, "max": 0.12701295018196107, "count": 2425 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2425 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2425 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2425 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2425 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2425 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2425 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1723619048", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/ebrahim/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723685408" }, "total": 66360.02898156899, "count": 1, "self": 0.27841117199568544, "children": { "run_training.setup": { "total": 0.008874214996467344, "count": 1, "self": 0.008874214996467344 }, "TrainerController.start_learning": { "total": 66359.741696182, "count": 1, "self": 50.693213934238884, "children": { "TrainerController._reset_env": { "total": 4.127004659996601, "count": 250, "self": 4.127004659996601 }, "TrainerController.advance": { "total": 66304.83236201477, "count": 3451573, "self": 53.6562136716675, "children": { "env_step": { "total": 40765.52772757219, "count": 3451573, "self": 30595.85250927398, "children": { "SubprocessEnvManager._take_step": { "total": 10137.338691119716, "count": 3451573, "self": 327.56776049335895, "children": { "TorchPolicy.evaluate": { "total": 9809.770930626357, "count": 6277228, "self": 9809.770930626357 } } }, "workers": { "total": 32.33652717849327, "count": 3451573, "self": 0.0, "children": { "worker_root": { "total": 66291.60396756201, "count": 3451573, "is_parallel": true, "self": 41423.69997397126, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.010885266994591802, "count": 2, "is_parallel": true, "self": 0.009947107988409698, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009381590061821043, "count": 8, "is_parallel": true, "self": 0.0009381590061821043 } } }, "UnityEnvironment.step": { "total": 0.01445402399986051, "count": 1, "is_parallel": true, "self": 0.0004037000035168603, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026254499971400946, "count": 1, "is_parallel": true, "self": 0.00026254499971400946 }, "communicator.exchange": { "total": 0.01287272600166034, "count": 1, "is_parallel": true, "self": 0.01287272600166034 }, "steps_from_proto": { "total": 0.0009150529949693009, "count": 2, "is_parallel": true, "self": 0.00018889099737862125, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007261619975906797, "count": 8, "is_parallel": true, "self": 0.0007261619975906797 } } } } } } }, "UnityEnvironment.step": { "total": 24867.656315072643, "count": 3451572, "is_parallel": true, "self": 1315.5331290081376, "children": { "UnityEnvironment._generate_step_input": { "total": 786.1480543400539, "count": 3451572, "is_parallel": true, "self": 786.1480543400539 }, "communicator.exchange": { "total": 19266.03309211156, "count": 3451572, "is_parallel": true, "self": 19266.03309211156 }, "steps_from_proto": { "total": 3499.9420396128917, "count": 6903144, "is_parallel": true, "self": 668.6696489963724, "children": { "_process_rank_one_or_two_observation": { "total": 2831.2723906165193, "count": 27612576, "is_parallel": true, "self": 2831.2723906165193 } } } } }, "steps_from_proto": { "total": 0.2476785181061132, "count": 498, "is_parallel": true, "self": 0.04834417522943113, "children": { "_process_rank_one_or_two_observation": { "total": 0.19933434287668206, "count": 1992, "is_parallel": true, "self": 0.19933434287668206 } } } } } } } } }, "trainer_advance": { "total": 25485.64842077092, "count": 3451573, "self": 376.1763542408444, "children": { "process_trajectory": { "total": 6040.391007775252, "count": 3451573, "self": 6029.898756840303, "children": { "RLTrainer._checkpoint": { "total": 10.49225093494897, "count": 100, "self": 10.49225093494897 } } }, "_update_policy": { "total": 19069.081058754826, "count": 2425, "self": 3706.387782863567, "children": { "TorchPOCAOptimizer.update": { "total": 15362.693275891259, "count": 72759, "self": 15362.693275891259 } } } } } } }, "trainer_threads": { "total": 5.469919415190816e-07, "count": 1, "self": 5.469919415190816e-07 }, "TrainerController._save_models": { "total": 0.08911502599949017, "count": 1, "self": 0.0023540719994343817, "children": { "RLTrainer._checkpoint": { "total": 0.08676095400005579, "count": 1, "self": 0.08676095400005579 } } } } } } }