{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5697529315948486, "min": 0.5697529315948486, "max": 1.4282350540161133, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 17083.47265625, "min": 17083.47265625, "max": 43326.9375, "count": 33 }, "Pyramids.Step.mean": { "value": 989958.0, "min": 29952.0, "max": 989958.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989958.0, "min": 29952.0, "max": 989958.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.027781447395682335, "min": -0.1567494124174118, "max": 0.10649461299180984, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 6.806454658508301, "min": -37.14961242675781, "max": 26.410663604736328, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.09998150169849396, "min": -0.10298889875411987, "max": 0.6416728496551514, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -24.495468139648438, "min": -25.54124641418457, "max": 152.0764617919922, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06580670452386897, "min": 0.06420853877676838, "max": 0.07175141374133338, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9212938633341656, "min": 0.48710751419233944, "max": 1.0241472059318695, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01111924657790533, "min": 0.0004095529458446011, "max": 0.014578841951562237, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.15566945209067462, "min": 0.005324188295979814, "max": 0.20122647359237497, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.454518943764286e-06, "min": 7.454518943764286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.0001043632652127, "min": 0.0001043632652127, "max": 0.0035073866308712003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248480714285713, "min": 0.10248480714285713, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4347872999999998, "min": 1.3886848, "max": 2.5691288000000005, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002582322335714286, "min": 0.0002582322335714286, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036152512700000005, "min": 0.0036152512700000005, "max": 0.11693596712000001, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.017260180786252022, "min": 0.01671287976205349, "max": 0.701418399810791, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.2416425347328186, "min": 0.23398031294345856, "max": 4.909928798675537, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 786.2162162162163, "min": 745.8947368421053, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29090.0, "min": 15984.0, "max": 33200.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 0.04995785339882499, "min": -1.0000000521540642, "max": 0.3417729368886432, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 1.8983984291553497, "min": -30.993601590394974, "max": 12.645598664879799, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 0.04995785339882499, "min": -1.0000000521540642, "max": 0.3417729368886432, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 1.8983984291553497, "min": -30.993601590394974, "max": 12.645598664879799, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.14105907934687198, "min": 0.1294292282388621, "max": 13.87622656673193, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 5.360245015181135, "min": 4.788881444837898, "max": 222.01962506771088, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1769141633", "python_version": "3.8.20 (default, Sep 7 2024, 18:35:08) \n[GCC 11.4.0]", "command_line_arguments": "/home/cfmy/rl/deep-rl-class-zh/.venv38/bin/mlagents-learn --force ./ml-agents/config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids_Training --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.23.5", "end_time_seconds": "1769143283" }, "total": 1649.3432424259954, "count": 1, "self": 0.5271806520031532, "children": { "run_training.setup": { "total": 0.023424899991368875, "count": 1, "self": 0.023424899991368875 }, "TrainerController.start_learning": { "total": 1648.792636874001, "count": 1, "self": 1.3130523440631805, "children": { "TrainerController._reset_env": { "total": 2.4656410420138855, "count": 1, "self": 2.4656410420138855 }, "TrainerController.advance": { "total": 1644.9661176809168, "count": 63242, "self": 1.279258410053444, "children": { "env_step": { "total": 1170.0897326112463, "count": 63242, "self": 1097.9548885850818, "children": { "SubprocessEnvManager._take_step": { "total": 71.33310817070014, "count": 63242, "self": 3.0629787500802195, "children": { "TorchPolicy.evaluate": { "total": 68.27012942061992, "count": 62566, "self": 14.928763125877595, "children": { "TorchPolicy.sample_actions": { "total": 53.34136629474233, "count": 62566, "self": 53.34136629474233 } } } } }, "workers": { "total": 0.8017358554643579, "count": 63242, "self": 0.0, "children": { "worker_root": { "total": 1645.669839021968, "count": 63242, "is_parallel": true, "self": 628.1513156488363, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018416250095469877, "count": 1, "is_parallel": true, "self": 0.0006031470111338422, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012384779984131455, "count": 8, "is_parallel": true, "self": 0.0012384779984131455 } } }, "UnityEnvironment.step": { "total": 0.03076878099818714, "count": 1, "is_parallel": true, "self": 0.00022137799533084035, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003743050037883222, "count": 1, "is_parallel": true, "self": 0.0003743050037883222 }, "communicator.exchange": { "total": 0.029574961998150684, "count": 1, "is_parallel": true, "self": 0.029574961998150684 }, "steps_from_proto": { "total": 0.0005981360009172931, "count": 1, "is_parallel": true, "self": 0.00016027498350013047, "children": { "_process_rank_one_or_two_observation": { "total": 0.00043786101741716266, "count": 8, "is_parallel": true, "self": 0.00043786101741716266 } } } } } } }, "UnityEnvironment.step": { "total": 1017.5185233731318, "count": 63241, "is_parallel": true, "self": 14.65468421546393, "children": { "UnityEnvironment._generate_step_input": { "total": 9.33519983770384, "count": 63241, "is_parallel": true, "self": 9.33519983770384 }, "communicator.exchange": { "total": 955.8037445731752, "count": 63241, "is_parallel": true, "self": 955.8037445731752 }, "steps_from_proto": { "total": 37.72489474678878, "count": 63241, "is_parallel": true, "self": 10.440495088492753, "children": { "_process_rank_one_or_two_observation": { "total": 27.284399658296024, "count": 505928, "is_parallel": true, "self": 27.284399658296024 } } } } } } } } } } }, "trainer_advance": { "total": 473.59712665961706, "count": 63242, "self": 2.243827484344365, "children": { "process_trajectory": { "total": 91.52122798137134, "count": 63242, "self": 91.40228566036967, "children": { "RLTrainer._checkpoint": { "total": 0.11894232100166846, "count": 2, "self": 0.11894232100166846 } } }, "_update_policy": { "total": 379.83207119390136, "count": 447, "self": 110.84842566719453, "children": { "TorchPPOOptimizer.update": { "total": 268.9836455267068, "count": 22779, "self": 268.9836455267068 } } } } } } }, "trainer_threads": { "total": 6.990012479946017e-07, "count": 1, "self": 6.990012479946017e-07 }, "TrainerController._save_models": { "total": 0.04782510800578166, "count": 1, "self": 0.0008432119939243421, "children": { "RLTrainer._checkpoint": { "total": 0.046981896011857316, "count": 1, "self": 0.046981896011857316 } } } } } } }