{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9806506037712097, "min": 0.9806506037712097, "max": 2.8608791828155518, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9320.103515625, "min": 9320.103515625, "max": 29203.853515625, "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": 13.16352367401123, "min": 0.2675674259662628, "max": 13.16352367401123, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2566.88720703125, "min": 51.9080810546875, "max": 2645.703857421875, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06802802224624696, "min": 0.0628585096616435, "max": 0.07273902487370423, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27211208898498784, "min": 0.251434038646574, "max": 0.36369512436852114, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18540163301661905, "min": 0.11987901202804756, "max": 0.2959917340354592, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7416065320664762, "min": 0.47951604811219023, "max": 1.3714995489400976, "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": 25.90909090909091, "min": 3.272727272727273, "max": 25.927272727272726, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1140.0, "min": 144.0, "max": 1426.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.90909090909091, "min": 3.272727272727273, "max": 25.927272727272726, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1140.0, "min": 144.0, "max": 1426.0, "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": "1756574983", "python_version": "3.10.12 (main, May 27 2025, 17:12:29) [GCC 11.4.0]", "command_line_arguments": "/root/DeepRL_HuggingFace/Unit3/.venv/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": "1756575463" }, "total": 480.7718617669998, "count": 1, "self": 0.21915289999992638, "children": { "run_training.setup": { "total": 0.024531700000125056, "count": 1, "self": 0.024531700000125056 }, "TrainerController.start_learning": { "total": 480.52817716699974, "count": 1, "self": 0.3188417010082958, "children": { "TrainerController._reset_env": { "total": 2.5686239069998464, "count": 1, "self": 2.5686239069998464 }, "TrainerController.advance": { "total": 477.541170858992, "count": 18192, "self": 0.3110575979787882, "children": { "env_step": { "total": 340.06852876199855, "count": 18192, "self": 234.26361332295846, "children": { "SubprocessEnvManager._take_step": { "total": 105.60814883905164, "count": 18192, "self": 1.0948364020596273, "children": { "TorchPolicy.evaluate": { "total": 104.51331243699201, "count": 18192, "self": 104.51331243699201 } } }, "workers": { "total": 0.19676659998845025, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 479.4417778620084, "count": 18192, "is_parallel": true, "self": 265.4219448909946, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025632000001678534, "count": 1, "is_parallel": true, "self": 0.0014231999998628453, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011400000003050081, "count": 10, "is_parallel": true, "self": 0.0011400000003050081 } } }, "UnityEnvironment.step": { "total": 0.02150819999997111, "count": 1, "is_parallel": true, "self": 0.00020810000000892614, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00016980000009425567, "count": 1, "is_parallel": true, "self": 0.00016980000009425567 }, "communicator.exchange": { "total": 0.0204522999999881, "count": 1, "is_parallel": true, "self": 0.0204522999999881 }, "steps_from_proto": { "total": 0.0006779999998798303, "count": 1, "is_parallel": true, "self": 0.000160700000151337, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005172999997284933, "count": 10, "is_parallel": true, "self": 0.0005172999997284933 } } } } } } }, "UnityEnvironment.step": { "total": 214.01983297101378, "count": 18191, "is_parallel": true, "self": 4.045821000982642, "children": { "UnityEnvironment._generate_step_input": { "total": 2.626018493007905, "count": 18191, "is_parallel": true, "self": 2.626018493007905 }, "communicator.exchange": { "total": 194.65295224205033, "count": 18191, "is_parallel": true, "self": 194.65295224205033 }, "steps_from_proto": { "total": 12.695041234972905, "count": 18191, "is_parallel": true, "self": 2.866156799055716, "children": { "_process_rank_one_or_two_observation": { "total": 9.828884435917189, "count": 181910, "is_parallel": true, "self": 9.828884435917189 } } } } } } } } } } }, "trainer_advance": { "total": 137.16158449901468, "count": 18192, "self": 0.42061359702938717, "children": { "process_trajectory": { "total": 27.58519571698389, "count": 18192, "self": 27.182226029984122, "children": { "RLTrainer._checkpoint": { "total": 0.4029696869997679, "count": 4, "self": 0.4029696869997679 } } }, "_update_policy": { "total": 109.1557751850014, "count": 90, "self": 22.795602454996242, "children": { "TorchPPOOptimizer.update": { "total": 86.36017273000516, "count": 4587, "self": 86.36017273000516 } } } } } } }, "trainer_threads": { "total": 6.999998731771484e-07, "count": 1, "self": 6.999998731771484e-07 }, "TrainerController._save_models": { "total": 0.0995399999997062, "count": 1, "self": 0.0009329999998044514, "children": { "RLTrainer._checkpoint": { "total": 0.09860699999990175, "count": 1, "self": 0.09860699999990175 } } } } } } }