{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.8164501190185547, "min": 1.7375110387802124, "max": 2.880383014678955, "count": 25 }, "SnowballTarget.Policy.Entropy.sum": { "value": 17243.560546875, "min": 16627.98046875, "max": 29593.0546875, "count": 25 }, "SnowballTarget.Step.mean": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Step.sum": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 57.39557647705078, "min": 0.25368398427963257, "max": 57.39557647705078, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 11134.7421875, "min": 49.214691162109375, "max": 11390.1767578125, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06899101311080136, "min": 0.06097532159713891, "max": 0.07470449159816638, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27596405244320543, "min": 0.26003843476064503, "max": 0.3735224579908319, "count": 25 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 1.0326211208514138, "min": 0.11895322224225703, "max": 1.0326211208514138, "count": 25 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 4.130484483405655, "min": 0.4758128889690281, "max": 4.672154927954955, "count": 25 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.9152980848e-06, "min": 1.9152980848e-06, "max": 9.783520216480001e-05, "count": 25 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 7.6611923392e-06, "min": 7.6611923392e-06, "max": 0.00046937603062400005, "count": 25 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10191520000000001, "min": 0.10191520000000001, "max": 0.19783520000000002, "count": 25 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40766080000000005, "min": 0.40766080000000005, "max": 0.9693760000000002, "count": 25 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00010556848000000002, "min": 0.00010556848000000002, "max": 0.004891976480000001, "count": 25 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004222739200000001, "min": 0.0004222739200000001, "max": 0.023471862399999998, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 17.045454545454547, "min": 3.0, "max": 17.045454545454547, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 750.0, "min": 132.0, "max": 924.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 17.045454545454547, "min": 3.0, "max": 17.045454545454547, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 750.0, "min": 132.0, "max": 924.0, "count": 25 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704622442", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704622967" }, "total": 525.4039552710019, "count": 1, "self": 0.22012561200244818, "children": { "run_training.setup": { "total": 0.03022409899858758, "count": 1, "self": 0.03022409899858758 }, "TrainerController.start_learning": { "total": 525.1536055600009, "count": 1, "self": 0.5520739039275213, "children": { "TrainerController._reset_env": { "total": 1.5216524229981587, "count": 1, "self": 1.5216524229981587 }, "TrainerController.advance": { "total": 523.0146514130756, "count": 22739, "self": 0.26972076579841087, "children": { "env_step": { "total": 522.7449306472772, "count": 22739, "self": 295.4358583427893, "children": { "SubprocessEnvManager._take_step": { "total": 227.0432843540766, "count": 22739, "self": 1.7107403559275554, "children": { "TorchPolicy.evaluate": { "total": 225.33254399814905, "count": 22739, "self": 225.33254399814905 } } }, "workers": { "total": 0.2657879504113225, "count": 22739, "self": 0.0, "children": { "worker_root": { "total": 524.1977550026713, "count": 22739, "is_parallel": true, "self": 307.0990864052874, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002045086002908647, "count": 1, "is_parallel": true, "self": 0.0008155110117513686, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012295749911572784, "count": 10, "is_parallel": true, "self": 0.0012295749911572784 } } }, "UnityEnvironment.step": { "total": 0.019248625998443458, "count": 1, "is_parallel": true, "self": 0.00024717499763937667, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017118299729190767, "count": 1, "is_parallel": true, "self": 0.00017118299729190767 }, "communicator.exchange": { "total": 0.01817365000169957, "count": 1, "is_parallel": true, "self": 0.01817365000169957 }, "steps_from_proto": { "total": 0.0006566180018126033, "count": 1, "is_parallel": true, "self": 0.00016765701002441347, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004889609917881899, "count": 10, "is_parallel": true, "self": 0.0004889609917881899 } } } } } } }, "UnityEnvironment.step": { "total": 217.09866859738395, "count": 22738, "is_parallel": true, "self": 5.130917855909502, "children": { "UnityEnvironment._generate_step_input": { "total": 3.0533657258347375, "count": 22738, "is_parallel": true, "self": 3.0533657258347375 }, "communicator.exchange": { "total": 195.0523249384496, "count": 22738, "is_parallel": true, "self": 195.0523249384496 }, "steps_from_proto": { "total": 13.862060077190108, "count": 22738, "is_parallel": true, "self": 3.2647140835179016, "children": { "_process_rank_one_or_two_observation": { "total": 10.597345993672207, "count": 227380, "is_parallel": true, "self": 10.597345993672207 } } } } } } } } } } } } }, "trainer_threads": { "total": 8.766300015849993e-05, "count": 1, "self": 8.766300015849993e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 520.0632006218948, "count": 485964, "is_parallel": true, "self": 8.86695256679377, "children": { "process_trajectory": { "total": 284.5820588210772, "count": 485964, "is_parallel": true, "self": 284.0855083270799, "children": { "RLTrainer._checkpoint": { "total": 0.4965504939973471, "count": 5, "is_parallel": true, "self": 0.4965504939973471 } } }, "_update_policy": { "total": 226.6141892340238, "count": 113, "is_parallel": true, "self": 31.510071466924273, "children": { "TorchPPOOptimizer.update": { "total": 195.10411776709952, "count": 5760, "is_parallel": true, "self": 195.10411776709952 } } } } } } } } }, "TrainerController._save_models": { "total": 0.06514015699940501, "count": 1, "self": 0.0005000460005248897, "children": { "RLTrainer._checkpoint": { "total": 0.06464011099888012, "count": 1, "self": 0.06464011099888012 } } } } } } }