{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8099718689918518, "min": 0.8099718689918518, "max": 2.8536765575408936, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7697.97265625, "min": 7697.97265625, "max": 29130.330078125, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.916003227233887, "min": 0.5392415523529053, "max": 12.916003227233887, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2518.62060546875, "min": 104.61286163330078, "max": 2604.22802734375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06734189498934473, "min": 0.06291075544272019, "max": 0.07607090198457717, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2693675799573789, "min": 0.2555370254955122, "max": 0.3757095791327575, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19281112366155082, "min": 0.1654247013788086, "max": 0.2743921930737355, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7712444946462033, "min": 0.6616988055152344, "max": 1.3586040700183193, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.454545454545453, "min": 4.295454545454546, "max": 25.581818181818182, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 189.0, "max": 1407.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 4.295454545454546, "max": 25.581818181818182, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 189.0, "max": 1407.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1756461464", "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]", "command_line_arguments": "/home/sam/.local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1756461825" }, "total": 347.7700018680007, "count": 1, "self": 0.21937220599829743, "children": { "run_training.setup": { "total": 0.022970487001657602, "count": 1, "self": 0.022970487001657602 }, "TrainerController.start_learning": { "total": 347.52765917500074, "count": 1, "self": 0.2953650409071997, "children": { "TrainerController._reset_env": { "total": 2.2293939080009295, "count": 1, "self": 2.2293939080009295 }, "TrainerController.advance": { "total": 344.9352438640926, "count": 18192, "self": 0.27923387623195595, "children": { "env_step": { "total": 252.5608371729595, "count": 18192, "self": 172.87266353395717, "children": { "SubprocessEnvManager._take_step": { "total": 79.5130555319738, "count": 18192, "self": 0.922468826176555, "children": { "TorchPolicy.evaluate": { "total": 78.59058670579725, "count": 18192, "self": 78.59058670579725 } } }, "workers": { "total": 0.17511810702853836, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 346.67924444593154, "count": 18192, "is_parallel": true, "self": 190.63452843593768, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021564409998973133, "count": 1, "is_parallel": true, "self": 0.0012013230025331723, "children": { "_process_rank_one_or_two_observation": { "total": 0.000955117997364141, "count": 10, "is_parallel": true, "self": 0.000955117997364141 } } }, "UnityEnvironment.step": { "total": 0.019940128999223816, "count": 1, "is_parallel": true, "self": 0.00023346999660134315, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019274200167274103, "count": 1, "is_parallel": true, "self": 0.00019274200167274103 }, "communicator.exchange": { "total": 0.018983380001373007, "count": 1, "is_parallel": true, "self": 0.018983380001373007 }, "steps_from_proto": { "total": 0.0005305369995767251, "count": 1, "is_parallel": true, "self": 0.00011946199992962647, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004110749996470986, "count": 10, "is_parallel": true, "self": 0.0004110749996470986 } } } } } } }, "UnityEnvironment.step": { "total": 156.04471600999386, "count": 18191, "is_parallel": true, "self": 3.3709146830806276, "children": { "UnityEnvironment._generate_step_input": { "total": 1.9072834200323996, "count": 18191, "is_parallel": true, "self": 1.9072834200323996 }, "communicator.exchange": { "total": 141.72387431691823, "count": 18191, "is_parallel": true, "self": 141.72387431691823 }, "steps_from_proto": { "total": 9.042643589962609, "count": 18191, "is_parallel": true, "self": 1.9805277971263422, "children": { "_process_rank_one_or_two_observation": { "total": 7.062115792836266, "count": 181910, "is_parallel": true, "self": 7.062115792836266 } } } } } } } } } } }, "trainer_advance": { "total": 92.09517281490116, "count": 18192, "self": 0.35047943067911547, "children": { "process_trajectory": { "total": 19.03807237223191, "count": 18192, "self": 18.706126988232427, "children": { "RLTrainer._checkpoint": { "total": 0.33194538399948215, "count": 4, "self": 0.33194538399948215 } } }, "_update_policy": { "total": 72.70662101199014, "count": 90, "self": 15.631592218032893, "children": { "TorchPPOOptimizer.update": { "total": 57.075028793957244, "count": 4587, "self": 57.075028793957244 } } } } } } }, "trainer_threads": { "total": 4.699995770351961e-07, "count": 1, "self": 4.699995770351961e-07 }, "TrainerController._save_models": { "total": 0.06765589200040267, "count": 1, "self": 0.001078233999578515, "children": { "RLTrainer._checkpoint": { "total": 0.06657765800082416, "count": 1, "self": 0.06657765800082416 } } } } } } }