{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6372256278991699, "min": 0.6304492354393005, "max": 0.7413288354873657, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6448.72314453125, "min": 6123.5537109375, "max": 7600.10302734375, "count": 20 }, "SnowballTarget.Step.mean": { "value": 599952.0, "min": 409984.0, "max": 599952.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 599952.0, "min": 409984.0, "max": 599952.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.573698997497559, "min": 13.207062721252441, "max": 13.67253303527832, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2646.871337890625, "min": 2562.0791015625, "max": 2789.19677734375, "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": 0.06944811620101687, "min": 0.06160803573610096, "max": 0.07471052457951695, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2777924648040675, "min": 0.26201602920841915, "max": 0.37355262289758473, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1575547485959296, "min": 0.1575547485959296, "max": 0.20449341912114738, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6302189943837184, "min": 0.6302189943837184, "max": 0.9703168766755683, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 2.582099139333337e-06, "min": 2.582099139333337e-06, "max": 9.718206760599997e-05, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.0328396557333347e-05, "min": 1.0328396557333347e-05, "max": 0.00046116034627999996, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10086066666666667, "min": 0.10086066666666667, "max": 0.13239400000000004, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40344266666666667, "min": 0.40344266666666667, "max": 0.6537200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 5.294726666666673e-05, "min": 5.294726666666673e-05, "max": 0.0016264606000000003, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0002117890666666669, "min": 0.0002117890666666669, "max": 0.007720628000000001, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.795454545454547, "min": 25.59090909090909, "max": 27.036363636363635, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1179.0, "min": 1126.0, "max": 1487.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.795454545454547, "min": 25.59090909090909, "max": 27.036363636363635, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1179.0, "min": 1126.0, "max": 1487.0, "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": "1694837635", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --resume --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1694838002" }, "total": 367.19065737000005, "count": 1, "self": 0.273493672000086, "children": { "run_training.setup": { "total": 0.0454269409999597, "count": 1, "self": 0.0454269409999597 }, "TrainerController.start_learning": { "total": 366.871736757, "count": 1, "self": 0.5238358360088569, "children": { "TrainerController._reset_env": { "total": 4.027539482000066, "count": 1, "self": 4.027539482000066 }, "TrainerController.advance": { "total": 362.1868134979911, "count": 18202, "self": 0.22542344800422143, "children": { "env_step": { "total": 361.9613900499869, "count": 18202, "self": 266.93687646594435, "children": { "SubprocessEnvManager._take_step": { "total": 94.78736859001924, "count": 18202, "self": 1.3577274790309275, "children": { "TorchPolicy.evaluate": { "total": 93.42964111098831, "count": 18202, "self": 93.42964111098831 } } }, "workers": { "total": 0.23714499402331057, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 366.10896869898716, "count": 18202, "is_parallel": true, "self": 183.55066692399282, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001986266999892905, "count": 1, "is_parallel": true, "self": 0.0006178289997933462, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013684380000995588, "count": 10, "is_parallel": true, "self": 0.0013684380000995588 } } }, "UnityEnvironment.step": { "total": 0.027899336000018593, "count": 1, "is_parallel": true, "self": 0.00042182799984402664, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002940250001302047, "count": 1, "is_parallel": true, "self": 0.0002940250001302047 }, "communicator.exchange": { "total": 0.025274244000002, "count": 1, "is_parallel": true, "self": 0.025274244000002 }, "steps_from_proto": { "total": 0.001909239000042362, "count": 1, "is_parallel": true, "self": 0.0009877020002022618, "children": { "_process_rank_one_or_two_observation": { "total": 0.0009215369998401002, "count": 10, "is_parallel": true, "self": 0.0009215369998401002 } } } } } } }, "UnityEnvironment.step": { "total": 182.55830177499433, "count": 18201, "is_parallel": true, "self": 7.33239924293639, "children": { "UnityEnvironment._generate_step_input": { "total": 3.7956068410185253, "count": 18201, "is_parallel": true, "self": 3.7956068410185253 }, "communicator.exchange": { "total": 147.8650812430094, "count": 18201, "is_parallel": true, "self": 147.8650812430094 }, "steps_from_proto": { "total": 23.56521444803002, "count": 18201, "is_parallel": true, "self": 4.305381379084338, "children": { "_process_rank_one_or_two_observation": { "total": 19.25983306894568, "count": 182010, "is_parallel": true, "self": 19.25983306894568 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003036520001842291, "count": 1, "self": 0.0003036520001842291, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 361.23940356398793, "count": 211361, "is_parallel": true, "self": 3.6314317079313696, "children": { "process_trajectory": { "total": 196.8941352970562, "count": 211361, "is_parallel": true, "self": 196.12222567305616, "children": { "RLTrainer._checkpoint": { "total": 0.7719096240000454, "count": 4, "is_parallel": true, "self": 0.7719096240000454 } } }, "_update_policy": { "total": 160.71383655900036, "count": 90, "is_parallel": true, "self": 46.63256134998596, "children": { "TorchPPOOptimizer.update": { "total": 114.0812752090144, "count": 4587, "is_parallel": true, "self": 114.0812752090144 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13324428899977647, "count": 1, "self": 0.001086108999516, "children": { "RLTrainer._checkpoint": { "total": 0.13215818000026047, "count": 1, "self": 0.13215818000026047 } } } } } } }