{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.288881301879883, "min": 3.282517910003662, "max": 3.295713424682617, "count": 4 }, "SoccerTwos.Policy.Entropy.sum": { "value": 65251.40625, "min": 45692.6484375, "max": 105462.765625, "count": 4 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 864.0, "min": 738.7777777777778, "max": 886.0, "count": 4 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 24192.0, "min": 15592.0, "max": 26596.0, "count": 4 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1198.025705444381, "min": 1198.025705444381, "max": 1198.6368125508247, "count": 4 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2396.051410888762, "min": 2396.051410888762, "max": 9589.094500406598, "count": 4 }, "SoccerTwos.Step.mean": { "value": 39876.0, "min": 9316.0, "max": 39876.0, "count": 4 }, "SoccerTwos.Step.sum": { "value": 39876.0, "min": 9316.0, "max": 39876.0, "count": 4 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.036910559982061386, "min": -0.04539959505200386, "max": -0.036910559982061386, "count": 4 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.4429267346858978, "min": -0.6355534195899963, "max": -0.4429267346858978, "count": 4 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04023938998579979, "min": -0.04540951922535896, "max": -0.04023938998579979, "count": 4 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.4828726649284363, "min": -0.6356660723686218, "max": -0.4828726649284363, "count": 4 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.1574666698773702, "min": -0.3723999985626766, "max": 0.1574666698773702, "count": 4 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.8896000385284424, "min": -5.213599979877472, "max": 1.8896000385284424, "count": 4 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.1574666698773702, "min": -0.3723999985626766, "max": 0.1574666698773702, "count": 4 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.8896000385284424, "min": -5.213599979877472, "max": 1.8896000385284424, "count": 4 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017958800479148825, "min": 0.017958800479148825, "max": 0.017958800479148825, "count": 1 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017958800479148825, "min": 0.017958800479148825, "max": 0.017958800479148825, "count": 1 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.00371873223533233, "min": 0.00371873223533233, "max": 0.00371873223533233, "count": 1 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.00371873223533233, "min": 0.00371873223533233, "max": 0.00371873223533233, "count": 1 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.003505130197542409, "min": 0.003505130197542409, "max": 0.003505130197542409, "count": 1 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.003505130197542409, "min": 0.003505130197542409, "max": 0.003505130197542409, "count": 1 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 1 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 1 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739481968", "python_version": "3.10.12 (main, Feb 13 2025, 10:55:24) [GCC 13.3.0]", "command_line_arguments": "/home/sdiaadmin/workshop/alex/hf_rl/ml-agents-env/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739482046" }, "total": 78.78807352704462, "count": 1, "self": 0.1325466490816325, "children": { "run_training.setup": { "total": 0.02017277997219935, "count": 1, "self": 0.02017277997219935 }, "TrainerController.start_learning": { "total": 78.63535409799078, "count": 1, "self": 0.05489160702563822, "children": { "TrainerController._reset_env": { "total": 2.275416558026336, "count": 1, "self": 2.275416558026336 }, "TrainerController.advance": { "total": 76.12623380793957, "count": 3013, "self": 0.04798580065835267, "children": { "env_step": { "total": 64.4578452668502, "count": 3013, "self": 49.03936653031269, "children": { "SubprocessEnvManager._take_step": { "total": 15.39188690361334, "count": 3013, "self": 0.3131978992023505, "children": { "TorchPolicy.evaluate": { "total": 15.07868900441099, "count": 6000, "self": 15.07868900441099 } } }, "workers": { "total": 0.026591832924168557, "count": 3013, "self": 0.0, "children": { "worker_root": { "total": 74.66723270865623, "count": 3013, "is_parallel": true, "self": 33.73665810591774, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006514078995678574, "count": 2, "is_parallel": true, "self": 0.0014143039006739855, "children": { "_process_rank_one_or_two_observation": { "total": 0.005099775095004588, "count": 8, "is_parallel": true, "self": 0.005099775095004588 } } }, "UnityEnvironment.step": { "total": 0.030795760976616293, "count": 1, "is_parallel": true, "self": 0.0008101999992504716, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00127127900486812, "count": 1, "is_parallel": true, "self": 0.00127127900486812 }, "communicator.exchange": { "total": 0.026238952996209264, "count": 1, "is_parallel": true, "self": 0.026238952996209264 }, "steps_from_proto": { "total": 0.002475328976288438, "count": 2, "is_parallel": true, "self": 0.0004469578852877021, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020283710910007358, "count": 8, "is_parallel": true, "self": 0.0020283710910007358 } } } } } } }, "UnityEnvironment.step": { "total": 40.93057460273849, "count": 3012, "is_parallel": true, "self": 1.482369762728922, "children": { "UnityEnvironment._generate_step_input": { "total": 0.9531680770451203, "count": 3012, "is_parallel": true, "self": 0.9531680770451203 }, "communicator.exchange": { "total": 33.82491795549868, "count": 3012, "is_parallel": true, "self": 33.82491795549868 }, "steps_from_proto": { "total": 4.670118807465769, "count": 6024, "is_parallel": true, "self": 0.8190037218737416, "children": { "_process_rank_one_or_two_observation": { "total": 3.8511150855920278, "count": 24096, "is_parallel": true, "self": 3.8511150855920278 } } } } } } } } } } }, "trainer_advance": { "total": 11.620402740431018, "count": 3013, "self": 0.36845785117475316, "children": { "process_trajectory": { "total": 3.6779552212683484, "count": 3013, "self": 3.6779552212683484 }, "_update_policy": { "total": 7.573989667987917, "count": 2, "self": 5.098582395003177, "children": { "TorchPOCAOptimizer.update": { "total": 2.4754072729847394, "count": 52, "self": 2.4754072729847394 } } } } } } }, "trainer_threads": { "total": 1.033011358231306e-06, "count": 1, "self": 1.033011358231306e-06 }, "TrainerController._save_models": { "total": 0.1788110919878818, "count": 1, "self": 0.0011170660145580769, "children": { "RLTrainer._checkpoint": { "total": 0.17769402597332373, "count": 1, "self": 0.17769402597332373 } } } } } } }