{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.34832340478897095, "min": 0.34832340478897095, "max": 1.4622364044189453, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10405.1171875, "min": 10405.1171875, "max": 44358.40234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989979.0, "min": 29952.0, "max": 989979.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989979.0, "min": 29952.0, "max": 989979.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.6554292440414429, "min": -0.11360462754964828, "max": 0.6554292440414429, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 191.38534545898438, "min": -27.37871551513672, "max": 191.38534545898438, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": 0.016062632203102112, "min": -0.004301663022488356, "max": 0.5802025198936462, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": 4.690288543701172, "min": -1.0668123960494995, "max": 137.50799560546875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06672628333866928, "min": 0.06493013817124026, "max": 0.07394129455067562, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9341679667413699, "min": 0.5006143359645355, "max": 1.0700096035434399, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.016255145767077227, "min": 0.0007360366355607995, "max": 0.01666574471681896, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.22757204073908116, "min": 0.009568476262290394, "max": 0.24998617075228444, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.220240450428572e-06, "min": 7.220240450428572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010108336630600001, "min": 0.00010108336630600001, "max": 0.0034917745360751994, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10240671428571431, "min": 0.10240671428571431, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4336940000000002, "min": 1.3886848, "max": 2.4851279, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025043075714285714, "min": 0.00025043075714285714, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035060306, "min": 0.0035060306, "max": 0.11640608752, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.01262574177235365, "min": 0.01262574177235365, "max": 0.5261805057525635, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.17676039040088654, "min": 0.17676039040088654, "max": 3.6832635402679443, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 290.578431372549, "min": 290.578431372549, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 29639.0, "min": 15984.0, "max": 32974.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.6920823342367715, "min": -1.0000000521540642, "max": 1.6920823342367715, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 172.5923980921507, "min": -29.783601693809032, "max": 172.5923980921507, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.6920823342367715, "min": -1.0000000521540642, "max": 1.6920823342367715, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 172.5923980921507, "min": -29.783601693809032, "max": 172.5923980921507, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03795710252654994, "min": 0.03795710252654994, "max": 12.040004938840866, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 3.8716244577080943, "min": 3.8716244577080943, "max": 192.64007902145386, "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": "1689293779", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1689296174" }, "total": 2394.7370083289998, "count": 1, "self": 0.48947118399928513, "children": { "run_training.setup": { "total": 0.04142073899993193, "count": 1, "self": 0.04142073899993193 }, "TrainerController.start_learning": { "total": 2394.2061164060005, "count": 1, "self": 1.6857448490013667, "children": { "TrainerController._reset_env": { "total": 5.473299649000182, "count": 1, "self": 5.473299649000182 }, "TrainerController.advance": { "total": 2386.945634285999, "count": 64012, "self": 1.6537900949761024, "children": { "env_step": { "total": 1706.0167622909635, "count": 64012, "self": 1580.1740359468063, "children": { "SubprocessEnvManager._take_step": { "total": 124.87054938201709, "count": 64012, "self": 5.269762554961289, "children": { "TorchPolicy.evaluate": { "total": 119.6007868270558, "count": 62555, "self": 119.6007868270558 } } }, "workers": { "total": 0.9721769621401108, "count": 64012, "self": 0.0, "children": { "worker_root": { "total": 2388.2770991890216, "count": 64012, "is_parallel": true, "self": 938.1089773259591, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002809275999879901, "count": 1, "is_parallel": true, "self": 0.000700279000284354, "children": { "_process_rank_one_or_two_observation": { "total": 0.002108996999595547, "count": 8, "is_parallel": true, "self": 0.002108996999595547 } } }, "UnityEnvironment.step": { "total": 0.05233556499979386, "count": 1, "is_parallel": true, "self": 0.000573656999222294, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000528467000094679, "count": 1, "is_parallel": true, "self": 0.000528467000094679 }, "communicator.exchange": { "total": 0.049266879000242625, "count": 1, "is_parallel": true, "self": 0.049266879000242625 }, "steps_from_proto": { "total": 0.001966562000234262, "count": 1, "is_parallel": true, "self": 0.0003941660011150816, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015723959991191805, "count": 8, "is_parallel": true, "self": 0.0015723959991191805 } } } } } } }, "UnityEnvironment.step": { "total": 1450.1681218630624, "count": 64011, "is_parallel": true, "self": 36.008163250022335, "children": { "UnityEnvironment._generate_step_input": { "total": 25.14850788496551, "count": 64011, "is_parallel": true, "self": 25.14850788496551 }, "communicator.exchange": { "total": 1272.351497321029, "count": 64011, "is_parallel": true, "self": 1272.351497321029 }, "steps_from_proto": { "total": 116.65995340704558, "count": 64011, "is_parallel": true, "self": 23.16387124790117, "children": { "_process_rank_one_or_two_observation": { "total": 93.49608215914441, "count": 512088, "is_parallel": true, "self": 93.49608215914441 } } } } } } } } } } }, "trainer_advance": { "total": 679.2750819000594, "count": 64012, "self": 3.0479437191411307, "children": { "process_trajectory": { "total": 122.30620107891082, "count": 64012, "self": 122.0765762099104, "children": { "RLTrainer._checkpoint": { "total": 0.22962486900041768, "count": 2, "self": 0.22962486900041768 } } }, "_update_policy": { "total": 553.9209371020074, "count": 449, "self": 356.27039495005147, "children": { "TorchPPOOptimizer.update": { "total": 197.65054215195596, "count": 22782, "self": 197.65054215195596 } } } } } } }, "trainer_threads": { "total": 1.0980002116411924e-06, "count": 1, "self": 1.0980002116411924e-06 }, "TrainerController._save_models": { "total": 0.10143652399983694, "count": 1, "self": 0.0018505890002415981, "children": { "RLTrainer._checkpoint": { "total": 0.09958593499959534, "count": 1, "self": 0.09958593499959534 } } } } } } }