{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.619049310684204, "min": 1.619049310684204, "max": 3.2956883907318115, "count": 1000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31396.603515625, "min": 18282.5, "max": 115885.4609375, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 46.660377358490564, "min": 45.66355140186916, "max": 999.0, "count": 1000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19784.0, "min": 9156.0, "max": 31876.0, "count": 1000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1583.2908266567183, "min": 1174.4644358660264, "max": 1600.7497911642322, "count": 990 }, "SoccerTwos.Self-play.ELO.sum": { "value": 335657.6552512243, "min": 2370.8536334395567, "max": 339084.33217810746, "count": 990 }, "SoccerTwos.Step.mean": { "value": 9999982.0, "min": 9954.0, "max": 9999982.0, "count": 1000 }, "SoccerTwos.Step.sum": { "value": 9999982.0, "min": 9954.0, "max": 9999982.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.00607228372246027, "min": -0.11751111596822739, "max": 0.21167558431625366, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.2812519073486328, "min": -18.80177879333496, "max": 22.583396911621094, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.002361964900046587, "min": -0.11942289024591446, "max": 0.20918215811252594, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.4983745813369751, "min": -19.08892822265625, "max": 22.341575622558594, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09993649376512138, "min": -0.6316222217347887, "max": 0.6275224503205747, "count": 1000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -21.086600184440613, "min": -52.99939978122711, "max": 61.49720013141632, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09993649376512138, "min": -0.6316222217347887, "max": 0.6275224503205747, "count": 1000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -21.086600184440613, "min": -52.99939978122711, "max": 61.49720013141632, "count": 1000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02385382152472933, "min": 0.010645401534687456, "max": 0.02385382152472933, "count": 480 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02385382152472933, "min": 0.010645401534687456, "max": 0.02385382152472933, "count": 480 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1010389839609464, "min": 0.00015815873339306564, "max": 0.11575197329123815, "count": 480 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1010389839609464, "min": 0.00015815873339306564, "max": 0.11575197329123815, "count": 480 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10250727211435635, "min": 0.00015888037111532564, "max": 0.11866774335503578, "count": 480 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10250727211435635, "min": 0.00015888037111532564, "max": 0.11866774335503578, "count": 480 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 480 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 480 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 480 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 480 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 480 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 480 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1718479331", "python_version": "3.10.14 (main, Jun 14 2024, 18:23:26) [GCC 11.4.0]", "command_line_arguments": "/home/ivan/Code/rl/hf/unit7/u7/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718492588" }, "total": 13257.191734499007, "count": 1, "self": 0.21883212600369006, "children": { "run_training.setup": { "total": 0.010704863001592457, "count": 1, "self": 0.010704863001592457 }, "TrainerController.start_learning": { "total": 13256.962197510002, "count": 1, "self": 11.19704046548577, "children": { "TrainerController._reset_env": { "total": 2.3967403589049354, "count": 50, "self": 2.3967403589049354 }, "TrainerController.advance": { "total": 13243.187545907567, "count": 678304, "self": 10.965911682753358, "children": { "env_step": { "total": 9734.517115767929, "count": 678304, "self": 7381.073501714622, "children": { "SubprocessEnvManager._take_step": { "total": 2346.105229501147, "count": 678304, "self": 59.2861431860365, "children": { "TorchPolicy.evaluate": { "total": 2286.8190863151103, "count": 1263196, "self": 2286.8190863151103 } } }, "workers": { "total": 7.338384552160278, "count": 678304, "self": 0.0, "children": { "worker_root": { "total": 13242.747293296328, "count": 678304, "is_parallel": true, "self": 7165.139361804351, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017898979713208973, "count": 2, "is_parallel": true, "self": 0.00042084691813215613, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013690510531887412, "count": 8, "is_parallel": true, "self": 0.0013690510531887412 } } }, "UnityEnvironment.step": { "total": 0.0187501460313797, "count": 1, "is_parallel": true, "self": 0.0003802470164373517, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003191750147379935, "count": 1, "is_parallel": true, "self": 0.0003191750147379935 }, "communicator.exchange": { "total": 0.016770449001342058, "count": 1, "is_parallel": true, "self": 0.016770449001342058 }, "steps_from_proto": { "total": 0.0012802749988622963, "count": 2, "is_parallel": true, "self": 0.00026854907628148794, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010117259225808084, "count": 8, "is_parallel": true, "self": 0.0010117259225808084 } } } } } } }, "UnityEnvironment.step": { "total": 6077.540349922841, "count": 678303, "is_parallel": true, "self": 317.6406598382746, "children": { "UnityEnvironment._generate_step_input": { "total": 190.51674898219062, "count": 678303, "is_parallel": true, "self": 190.51674898219062 }, "communicator.exchange": { "total": 4672.0610915617435, "count": 678303, "is_parallel": true, "self": 4672.0610915617435 }, "steps_from_proto": { "total": 897.3218495406327, "count": 1356606, "is_parallel": true, "self": 167.22421341767767, "children": { "_process_rank_one_or_two_observation": { "total": 730.097636122955, "count": 5426424, "is_parallel": true, "self": 730.097636122955 } } } } }, "steps_from_proto": { "total": 0.06758156913565472, "count": 98, "is_parallel": true, "self": 0.01229875162243843, "children": { "_process_rank_one_or_two_observation": { "total": 0.05528281751321629, "count": 392, "is_parallel": true, "self": 0.05528281751321629 } } } } } } } } }, "trainer_advance": { "total": 3497.704518456885, "count": 678304, "self": 85.6454694432905, "children": { "process_trajectory": { "total": 1227.5400425905827, "count": 678304, "self": 1223.2639663565205, "children": { "RLTrainer._checkpoint": { "total": 4.276076234062202, "count": 20, "self": 4.276076234062202 } } }, "_update_policy": { "total": 2184.519006423012, "count": 480, "self": 1017.7918696403503, "children": { "TorchPOCAOptimizer.update": { "total": 1166.7271367826615, "count": 14403, "self": 1166.7271367826615 } } } } } } }, "trainer_threads": { "total": 7.2503462433815e-07, "count": 1, "self": 7.2503462433815e-07 }, "TrainerController._save_models": { "total": 0.18087005300913006, "count": 1, "self": 0.0009355859947390854, "children": { "RLTrainer._checkpoint": { "total": 0.17993446701439098, "count": 1, "self": 0.17993446701439098 } } } } } } }