{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.921726644039154, "min": 0.921726644039154, "max": 2.869048595428467, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8820.923828125, "min": 8820.923828125, "max": 29445.044921875, "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": 12.656290054321289, "min": 0.3638283610343933, "max": 12.693205833435059, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2467.9765625, "min": 70.58270263671875, "max": 2589.4140625, "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.Losses.PolicyLoss.mean": { "value": 0.06395731891012367, "min": 0.06187180142339511, "max": 0.07897685625507353, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2558292756404947, "min": 0.24748720569358043, "max": 0.36626040106456653, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21776851193577637, "min": 0.12869044419437392, "max": 0.31128797063640523, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8710740477431055, "min": 0.5147617767774957, "max": 1.556439853182026, "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.CumulativeReward.mean": { "value": 24.318181818181817, "min": 3.25, "max": 25.4, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1070.0, "min": 143.0, "max": 1397.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.318181818181817, "min": 3.25, "max": 25.4, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1070.0, "min": 143.0, "max": 1397.0, "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": "1714645052", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/home/pietro/Progetti/AI/005-MlAgents-Unit5-HF/.venv3-10/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTargetdsd1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714645620" }, "total": 567.7222288930006, "count": 1, "self": 0.6218467190010415, "children": { "run_training.setup": { "total": 0.020414257000084035, "count": 1, "self": 0.020414257000084035 }, "TrainerController.start_learning": { "total": 567.0799679169995, "count": 1, "self": 0.5103640379747958, "children": { "TrainerController._reset_env": { "total": 3.4553032380008517, "count": 1, "self": 3.4553032380008517 }, "TrainerController.advance": { "total": 562.9980535400236, "count": 18202, "self": 0.23809769406580017, "children": { "env_step": { "total": 562.7599558459578, "count": 18202, "self": 332.5064660880489, "children": { "SubprocessEnvManager._take_step": { "total": 229.994347996927, "count": 18202, "self": 1.556801870918207, "children": { "TorchPolicy.evaluate": { "total": 228.43754612600878, "count": 18202, "self": 228.43754612600878 } } }, "workers": { "total": 0.2591417609819473, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 566.1542695759154, "count": 18202, "is_parallel": true, "self": 312.4356956409347, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00369845300065208, "count": 1, "is_parallel": true, "self": 0.0020947770008206135, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016036759998314665, "count": 10, "is_parallel": true, "self": 0.0016036759998314665 } } }, "UnityEnvironment.step": { "total": 0.03076288200009003, "count": 1, "is_parallel": true, "self": 0.0003279980001025251, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021757700051239226, "count": 1, "is_parallel": true, "self": 0.00021757700051239226 }, "communicator.exchange": { "total": 0.029086523999467317, "count": 1, "is_parallel": true, "self": 0.029086523999467317 }, "steps_from_proto": { "total": 0.0011307830000077956, "count": 1, "is_parallel": true, "self": 0.0002498620024198317, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008809209975879639, "count": 10, "is_parallel": true, "self": 0.0008809209975879639 } } } } } } }, "UnityEnvironment.step": { "total": 253.71857393498067, "count": 18201, "is_parallel": true, "self": 5.217724076805098, "children": { "UnityEnvironment._generate_step_input": { "total": 2.9209072420308075, "count": 18201, "is_parallel": true, "self": 2.9209072420308075 }, "communicator.exchange": { "total": 229.78817997805254, "count": 18201, "is_parallel": true, "self": 229.78817997805254 }, "steps_from_proto": { "total": 15.791762638092223, "count": 18201, "is_parallel": true, "self": 3.62281502715814, "children": { "_process_rank_one_or_two_observation": { "total": 12.168947610934083, "count": 182010, "is_parallel": true, "self": 12.168947610934083 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014706399997521657, "count": 1, "self": 0.00014706399997521657, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 558.7350275819699, "count": 573531, "is_parallel": true, "self": 11.7732297948196, "children": { "process_trajectory": { "total": 323.8911240311472, "count": 573531, "is_parallel": true, "self": 323.1746811501471, "children": { "RLTrainer._checkpoint": { "total": 0.7164428810001482, "count": 4, "is_parallel": true, "self": 0.7164428810001482 } } }, "_update_policy": { "total": 223.0706737560031, "count": 90, "is_parallel": true, "self": 26.754162068983533, "children": { "TorchPPOOptimizer.update": { "total": 196.31651168701956, "count": 4584, "is_parallel": true, "self": 196.31651168701956 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11610003700025118, "count": 1, "self": 0.0012262300006113946, "children": { "RLTrainer._checkpoint": { "total": 0.11487380699963978, "count": 1, "self": 0.11487380699963978 } } } } } } }