{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.5425539016723633, "min": 0.5425539016723633, "max": 1.468619704246521, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 16346.064453125, "min": 16346.064453125, "max": 44552.046875, "count": 33 }, "Pyramids.Step.mean": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989972.0, "min": 29952.0, "max": 989972.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.41159680485725403, "min": -0.11817629635334015, "max": 0.41159680485725403, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 112.36592864990234, "min": -28.480487823486328, "max": 112.36592864990234, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0859936773777008, "min": -1.211134433746338, "max": 2.1595988273620605, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -23.476274490356445, "min": -311.26153564453125, "max": 557.176513671875, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06964862173837093, "min": 0.06676053485023745, "max": 0.07377512072322563, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 1.044729326075564, "min": 0.5080945445789993, "max": 1.0528265653045703, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.02242212637308209, "min": 0.00043283175787830314, "max": 0.6132332091218582, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.33633189559623133, "min": 0.0038954858209047285, "max": 9.198498136827872, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.4768175077600005e-06, "min": 7.4768175077600005e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00011215226261640001, "min": 0.00011215226261640001, "max": 0.0030070069976644, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10249224, "min": 0.10249224, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.5373836, "min": 1.3886848, "max": 2.3926580000000004, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002589747760000001, "min": 0.0002589747760000001, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.003884621640000001, "min": 0.003884621640000001, "max": 0.10025332644, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.00862919818609953, "min": 0.008608328178524971, "max": 0.34311988949775696, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.12943796813488007, "min": 0.12051659822463989, "max": 2.401839256286621, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 392.02777777777777, "min": 392.02777777777777, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 28226.0, "min": 15984.0, "max": 33178.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.580419156036965, "min": -1.0000000521540642, "max": 1.580419156036965, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 115.37059839069843, "min": -30.999801620841026, "max": 115.37059839069843, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.580419156036965, "min": -1.0000000521540642, "max": 1.580419156036965, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 115.37059839069843, "min": -30.999801620841026, "max": 115.37059839069843, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.03538861969200422, "min": 0.03538861969200422, "max": 7.488560322672129, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 2.583369237516308, "min": 2.5102338370488724, "max": 119.81696516275406, "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": "1688477241", "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": "1688479316" }, "total": 2075.3085230530005, "count": 1, "self": 0.4743079080003554, "children": { "run_training.setup": { "total": 0.03737399900001037, "count": 1, "self": 0.03737399900001037 }, "TrainerController.start_learning": { "total": 2074.796841146, "count": 1, "self": 1.2344925670058728, "children": { "TrainerController._reset_env": { "total": 4.260089194000102, "count": 1, "self": 4.260089194000102 }, "TrainerController.advance": { "total": 2069.2089239729935, "count": 63542, "self": 1.3632959320025293, "children": { "env_step": { "total": 1445.5772854350007, "count": 63542, "self": 1341.8772181949712, "children": { "SubprocessEnvManager._take_step": { "total": 102.97800759501251, "count": 63542, "self": 4.5506318940765595, "children": { "TorchPolicy.evaluate": { "total": 98.42737570093595, "count": 62559, "self": 98.42737570093595 } } }, "workers": { "total": 0.7220596450169978, "count": 63542, "self": 0.0, "children": { "worker_root": { "total": 2070.200419161969, "count": 63542, "is_parallel": true, "self": 835.2634478619243, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001827699999921606, "count": 1, "is_parallel": true, "self": 0.0005811420005557011, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012465579993659048, "count": 8, "is_parallel": true, "self": 0.0012465579993659048 } } }, "UnityEnvironment.step": { "total": 0.0884340779998638, "count": 1, "is_parallel": true, "self": 0.0005736929997510742, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000507522000134486, "count": 1, "is_parallel": true, "self": 0.000507522000134486 }, "communicator.exchange": { "total": 0.08551485799989678, "count": 1, "is_parallel": true, "self": 0.08551485799989678 }, "steps_from_proto": { "total": 0.0018380050000814663, "count": 1, "is_parallel": true, "self": 0.0003565310003068589, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014814739997746074, "count": 8, "is_parallel": true, "self": 0.0014814739997746074 } } } } } } }, "UnityEnvironment.step": { "total": 1234.9369713000447, "count": 63541, "is_parallel": true, "self": 32.25312550399394, "children": { "UnityEnvironment._generate_step_input": { "total": 22.245040674991287, "count": 63541, "is_parallel": true, "self": 22.245040674991287 }, "communicator.exchange": { "total": 1082.053668697943, "count": 63541, "is_parallel": true, "self": 1082.053668697943 }, "steps_from_proto": { "total": 98.38513642311636, "count": 63541, "is_parallel": true, "self": 18.98155933913904, "children": { "_process_rank_one_or_two_observation": { "total": 79.40357708397732, "count": 508328, "is_parallel": true, "self": 79.40357708397732 } } } } } } } } } } }, "trainer_advance": { "total": 622.2683426059903, "count": 63542, "self": 2.281052304993409, "children": { "process_trajectory": { "total": 104.51294166901334, "count": 63542, "self": 104.30979057901368, "children": { "RLTrainer._checkpoint": { "total": 0.2031510899996647, "count": 2, "self": 0.2031510899996647 } } }, "_update_policy": { "total": 515.4743486319835, "count": 437, "self": 330.22803220603737, "children": { "TorchPPOOptimizer.update": { "total": 185.24631642594613, "count": 22809, "self": 185.24631642594613 } } } } } } }, "trainer_threads": { "total": 1.0410003596916795e-06, "count": 1, "self": 1.0410003596916795e-06 }, "TrainerController._save_models": { "total": 0.09333437100031006, "count": 1, "self": 0.0013144550002834876, "children": { "RLTrainer._checkpoint": { "total": 0.09201991600002657, "count": 1, "self": 0.09201991600002657 } } } } } } }