{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.3649227619171143, "min": 1.3649227619171143, "max": 2.887261390686035, "count": 100 }, "SnowballTarget.Policy.Entropy.sum": { "value": 12792.0556640625, "min": 7719.53369140625, "max": 63424.46875, "count": 100 }, "SnowballTarget.Step.mean": { "value": 999992.0, "min": 9984.0, "max": 999992.0, "count": 100 }, "SnowballTarget.Step.sum": { "value": 999992.0, "min": 9984.0, "max": 999992.0, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 129.77369689941406, "min": 0.3260085880756378, "max": 129.77369689941406, "count": 100 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 25305.87109375, "min": 50.857337951660156, "max": 29956.22265625, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06919076865896762, "min": 0.0644886161349053, "max": 0.0770839796147768, "count": 100 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27676307463587047, "min": 0.2134361763341273, "max": 0.38028132438440104, "count": 100 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17835985341054553, "min": 0.1263169656924027, "max": 0.3594714319959533, "count": 100 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7134394136421821, "min": 0.5052678627696108, "max": 1.648630742997759, "count": 100 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.6900994619999973e-06, "min": 2.6900994619999973e-06, "max": 0.000496880000624, "count": 100 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.076039784799999e-05, "min": 1.076039784799999e-05, "max": 0.0023106240378751993, "count": 100 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10080700000000004, "min": 0.10080700000000004, "max": 0.249064, "count": 100 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40322800000000014, "min": 0.40322800000000014, "max": 1.1931872000000001, "count": 100 }, "SnowballTarget.Policy.Beta.mean": { "value": 3.684619999999998e-05, "min": 3.684619999999998e-05, "max": 0.0049688624, "count": 100 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00014738479999999992, "min": 0.00014738479999999992, "max": 0.02311002752, "count": 100 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 100 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 89 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 2189.0, "max": 30646.0, "count": 89 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.113636363636363, "min": 4.109090909090909, "max": 26.651515151515152, "count": 89 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1149.0, "min": 66.0, "max": 2425.0, "count": 89 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.113636363636363, "min": 4.109090909090909, "max": 26.651515151515152, "count": 89 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1149.0, "min": 66.0, "max": 2425.0, "count": 89 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1765015109", "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]", "command_line_arguments": "/home/aditya/learn/deep-rl-unit5/.venv/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=Snowball-Demo-new-5 --num-envs=32 --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": "1765016375" }, "total": 1265.8648096020002, "count": 1, "self": 1.6597277570003826, "children": { "run_training.setup": { "total": 0.5564212699999871, "count": 1, "self": 0.5564212699999871 }, "TrainerController.start_learning": { "total": 1263.648660575, "count": 1, "self": 0.2879379939961382, "children": { "TrainerController._reset_env": { "total": 4.656400228999928, "count": 1, "self": 4.656400228999928 }, "TrainerController.advance": { "total": 1258.5140962050039, "count": 3181, "self": 0.0670817150039511, "children": { "env_step": { "total": 1258.44701449, "count": 3181, "self": 525.7094047089603, "children": { "SubprocessEnvManager._take_step": { "total": 732.2506135730323, "count": 91827, "self": 8.66461881798432, "children": { "TorchPolicy.evaluate": { "total": 723.585994755048, "count": 91827, "self": 723.585994755048 } } }, "workers": { "total": 0.48699620800732646, "count": 3181, "self": 0.0, "children": { "worker_root": { "total": 40436.991450002155, "count": 91825, "is_parallel": true, "self": 39607.58924856114, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.14369855899963113, "count": 32, "is_parallel": true, "self": 0.07861754100076723, "children": { "_process_rank_one_or_two_observation": { "total": 0.0650810179988639, "count": 320, "is_parallel": true, "self": 0.0650810179988639 } } }, "UnityEnvironment.step": { "total": 1.1472691400001622, "count": 32, "is_parallel": true, "self": 0.016976720000798196, "children": { "UnityEnvironment._generate_step_input": { "total": 0.008622310999953697, "count": 32, "is_parallel": true, "self": 0.008622310999953697 }, "communicator.exchange": { "total": 1.0797740689993134, "count": 32, "is_parallel": true, "self": 1.0797740689993134 }, "steps_from_proto": { "total": 0.041896040000096946, "count": 32, "is_parallel": true, "self": 0.010983067999973173, "children": { "_process_rank_one_or_two_observation": { "total": 0.030912972000123773, "count": 320, "is_parallel": true, "self": 0.030912972000123773 } } } } } } }, "UnityEnvironment.step": { "total": 829.4022014410122, "count": 91793, "is_parallel": true, "self": 35.24987103703802, "children": { "UnityEnvironment._generate_step_input": { "total": 20.28181674298162, "count": 91793, "is_parallel": true, "self": 20.28181674298162 }, "communicator.exchange": { "total": 674.7396259830101, "count": 91793, "is_parallel": true, "self": 674.7396259830101 }, "steps_from_proto": { "total": 99.1308876779824, "count": 91793, "is_parallel": true, "self": 21.4014509329387, "children": { "_process_rank_one_or_two_observation": { "total": 77.7294367450437, "count": 917930, "is_parallel": true, "self": 77.7294367450437 } } } } } } } } } } } } }, "trainer_threads": { "total": 3.1498999987888965e-05, "count": 1, "self": 3.1498999987888965e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 1252.2307682778985, "count": 775187, "is_parallel": true, "self": 15.668586585833282, "children": { "process_trajectory": { "total": 380.59664603206306, "count": 775187, "is_parallel": true, "self": 376.49412350506293, "children": { "RLTrainer._checkpoint": { "total": 4.102522527000133, "count": 20, "is_parallel": true, "self": 4.102522527000133 } } }, "_update_policy": { "total": 855.9655356600023, "count": 435, "is_parallel": true, "self": 283.2245301109998, "children": { "TorchPPOOptimizer.update": { "total": 572.7410055490025, "count": 38080, "is_parallel": true, "self": 572.7410055490025 } } } } } } } } }, "TrainerController._save_models": { "total": 0.19019464799998786, "count": 1, "self": 0.0028110499999911553, "children": { "RLTrainer._checkpoint": { "total": 0.1873835979999967, "count": 1, "self": 0.1873835979999967 } } } } } } }