{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.778346061706543, "min": 0.7760685086250305, "max": 2.8323302268981934, "count": 50 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7465.8955078125, "min": 7459.63916015625, "max": 28912.427734375, "count": 50 }, "SnowballTarget.Step.mean": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Step.sum": { "value": 499976.0, "min": 9952.0, "max": 499976.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 14.46053695678711, "min": 0.36530283093452454, "max": 14.469643592834473, "count": 50 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2964.41015625, "min": 70.8687515258789, "max": 2966.27685546875, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06906648196608704, "min": 0.058018910541546106, "max": 0.0763130648651271, "count": 50 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3453324098304352, "min": 0.24563687803011441, "max": 0.37258500561766394, "count": 50 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.15450777668578952, "min": 0.11841040632148803, "max": 0.2911285329683154, "count": 50 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7725388834289476, "min": 0.4736416252859521, "max": 1.455642664841577, "count": 50 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 6.105698982400004e-06, "min": 6.105698982400004e-06, "max": 0.0005935056010824, "count": 50 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.052849491200002e-05, "min": 3.052849491200002e-05, "max": 0.0029081280153119998, "count": 50 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10101760000000001, "min": 0.10101760000000001, "max": 0.19891759999999997, "count": 50 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5050880000000001, "min": 0.41199040000000003, "max": 0.984688, "count": 50 }, "SnowballTarget.Policy.Beta.mean": { "value": 6.0778240000000044e-05, "min": 6.0778240000000044e-05, "max": 0.00494598824, "count": 50 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0003038912000000002, "min": 0.0003038912000000002, "max": 0.0242359312, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 50 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 28.29090909090909, "min": 3.8863636363636362, "max": 28.64814814814815, "count": 50 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1556.0, "min": 171.0, "max": 1568.0, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 28.29090909090909, "min": 3.8863636363636362, "max": 28.64814814814815, "count": 50 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1556.0, "min": 171.0, "max": 1568.0, "count": 50 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1738842721", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget4 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1738843928" }, "total": 1207.0769785840002, "count": 1, "self": 0.4925473890007197, "children": { "run_training.setup": { "total": 0.021088758000132657, "count": 1, "self": 0.021088758000132657 }, "TrainerController.start_learning": { "total": 1206.5633424369994, "count": 1, "self": 1.0259412320483534, "children": { "TrainerController._reset_env": { "total": 1.9535205480001423, "count": 1, "self": 1.9535205480001423 }, "TrainerController.advance": { "total": 1203.4633720739512, "count": 45464, "self": 1.020297928023865, "children": { "env_step": { "total": 818.2079761099676, "count": 45464, "self": 603.5839399959186, "children": { "SubprocessEnvManager._take_step": { "total": 214.01058432204763, "count": 45464, "self": 3.3997262710645373, "children": { "TorchPolicy.evaluate": { "total": 210.6108580509831, "count": 45464, "self": 210.6108580509831 } } }, "workers": { "total": 0.6134517920013423, "count": 45464, "self": 0.0, "children": { "worker_root": { "total": 1203.0193285940236, "count": 45464, "is_parallel": true, "self": 674.9602680760827, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022099800003161363, "count": 1, "is_parallel": true, "self": 0.0007236290007313073, "children": { "_process_rank_one_or_two_observation": { "total": 0.001486350999584829, "count": 10, "is_parallel": true, "self": 0.001486350999584829 } } }, "UnityEnvironment.step": { "total": 0.035761382000146114, "count": 1, "is_parallel": true, "self": 0.0005477479999171919, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003832249999504711, "count": 1, "is_parallel": true, "self": 0.0003832249999504711 }, "communicator.exchange": { "total": 0.03308638099997552, "count": 1, "is_parallel": true, "self": 0.03308638099997552 }, "steps_from_proto": { "total": 0.001744028000302933, "count": 1, "is_parallel": true, "self": 0.0003583989996513992, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013856290006515337, "count": 10, "is_parallel": true, "self": 0.0013856290006515337 } } } } } } }, "UnityEnvironment.step": { "total": 528.0590605179409, "count": 45463, "is_parallel": true, "self": 24.55672441486513, "children": { "UnityEnvironment._generate_step_input": { "total": 13.932740382035263, "count": 45463, "is_parallel": true, "self": 13.932740382035263 }, "communicator.exchange": { "total": 408.3952639410668, "count": 45463, "is_parallel": true, "self": 408.3952639410668 }, "steps_from_proto": { "total": 81.17433177997373, "count": 45463, "is_parallel": true, "self": 14.825467513813692, "children": { "_process_rank_one_or_two_observation": { "total": 66.34886426616004, "count": 454630, "is_parallel": true, "self": 66.34886426616004 } } } } } } } } } } }, "trainer_advance": { "total": 384.2350980359597, "count": 45464, "self": 1.3410349658888663, "children": { "process_trajectory": { "total": 124.30384383406499, "count": 45464, "self": 122.85314747306666, "children": { "RLTrainer._checkpoint": { "total": 1.4506963609983359, "count": 10, "self": 1.4506963609983359 } } }, "_update_policy": { "total": 258.59021923600585, "count": 227, "self": 99.0990100999561, "children": { "TorchPPOOptimizer.update": { "total": 159.49120913604975, "count": 11574, "self": 159.49120913604975 } } } } } } }, "trainer_threads": { "total": 8.309998520417139e-07, "count": 1, "self": 8.309998520417139e-07 }, "TrainerController._save_models": { "total": 0.12050775199986674, "count": 1, "self": 0.0009625279999454506, "children": { "RLTrainer._checkpoint": { "total": 0.11954522399992129, "count": 1, "self": 0.11954522399992129 } } } } } } }