{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.3629785180091858, "min": 0.3629785180091858, "max": 1.381202220916748, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 10970.6630859375, "min": 10970.6630859375, "max": 41900.15234375, "count": 33 }, "Pyramids.Step.mean": { "value": 989923.0, "min": 29952.0, "max": 989923.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989923.0, "min": 29952.0, "max": 989923.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.5185297131538391, "min": -0.11361656337976456, "max": 0.5199669599533081, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 142.59567260742188, "min": -27.495208740234375, "max": 142.59567260742188, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.0007706319447606802, "min": -0.0038600757252424955, "max": 0.5687241554260254, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -0.2119237780570984, "min": -1.0538007020950317, "max": 134.78762817382812, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.06808358181608908, "min": 0.06460124472782593, "max": 0.07404532025447566, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.953170145425247, "min": 0.5183172417813297, "max": 1.0631428699154069, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.01489074792403872, "min": 0.0004641336488500631, "max": 0.01489074792403872, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.20847047093654208, "min": 0.0055696037862007575, "max": 0.20847047093654208, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.386418966464286e-06, "min": 7.386418966464286e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010340986553050001, "min": 0.00010340986553050001, "max": 0.0035091503302833007, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10246210714285715, "min": 0.10246210714285715, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4344695, "min": 1.3886848, "max": 2.5697167, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.00025596450357142866, "min": 0.00025596450357142866, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0035835030500000016, "min": 0.0035835030500000016, "max": 0.11699469833000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.015169852413237095, "min": 0.015169852413237095, "max": 0.7073416113853455, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.21237793564796448, "min": 0.21237793564796448, "max": 4.951391220092773, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 363.87951807228916, "min": 363.87951807228916, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 30202.0, "min": 15984.0, "max": 33189.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.539706000093236, "min": -1.0000000521540642, "max": 1.539706000093236, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 127.79559800773859, "min": -29.99860156327486, "max": 127.79559800773859, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.539706000093236, "min": -1.0000000521540642, "max": 1.539706000093236, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 127.79559800773859, "min": -29.99860156327486, "max": 127.79559800773859, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.0576538419861526, "min": 0.0576538419861526, "max": 14.821849748492241, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.785268884850666, "min": 4.647147872412461, "max": 237.14959597587585, "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": "1695287179", "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/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": "1695289548" }, "total": 2369.67916342, "count": 1, "self": 0.9388045019995843, "children": { "run_training.setup": { "total": 0.0695516509999834, "count": 1, "self": 0.0695516509999834 }, "TrainerController.start_learning": { "total": 2368.6708072670003, "count": 1, "self": 1.447591151973029, "children": { "TrainerController._reset_env": { "total": 5.559287268999981, "count": 1, "self": 5.559287268999981 }, "TrainerController.advance": { "total": 2361.5039606250275, "count": 63846, "self": 1.4127476829739862, "children": { "env_step": { "total": 1668.2027355980838, "count": 63846, "self": 1554.5798072271073, "children": { "SubprocessEnvManager._take_step": { "total": 112.70991289297547, "count": 63846, "self": 4.884333738970724, "children": { "TorchPolicy.evaluate": { "total": 107.82557915400474, "count": 62567, "self": 107.82557915400474 } } }, "workers": { "total": 0.9130154780010002, "count": 63846, "self": 0.0, "children": { "worker_root": { "total": 2363.2466532369986, "count": 63846, "is_parallel": true, "self": 927.8772438930584, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00667688199996519, "count": 1, "is_parallel": true, "self": 0.004497283999967294, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021795979999978954, "count": 8, "is_parallel": true, "self": 0.0021795979999978954 } } }, "UnityEnvironment.step": { "total": 0.05334817400000702, "count": 1, "is_parallel": true, "self": 0.0006251579999911883, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000580050999985815, "count": 1, "is_parallel": true, "self": 0.000580050999985815 }, "communicator.exchange": { "total": 0.049171116000024995, "count": 1, "is_parallel": true, "self": 0.049171116000024995 }, "steps_from_proto": { "total": 0.0029718490000050224, "count": 1, "is_parallel": true, "self": 0.00039504000005763373, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025768089999473887, "count": 8, "is_parallel": true, "self": 0.0025768089999473887 } } } } } } }, "UnityEnvironment.step": { "total": 1435.36940934394, "count": 63845, "is_parallel": true, "self": 36.388756132871094, "children": { "UnityEnvironment._generate_step_input": { "total": 24.03203222203649, "count": 63845, "is_parallel": true, "self": 24.03203222203649 }, "communicator.exchange": { "total": 1263.8359045640555, "count": 63845, "is_parallel": true, "self": 1263.8359045640555 }, "steps_from_proto": { "total": 111.11271642497712, "count": 63845, "is_parallel": true, "self": 21.800600321027957, "children": { "_process_rank_one_or_two_observation": { "total": 89.31211610394917, "count": 510760, "is_parallel": true, "self": 89.31211610394917 } } } } } } } } } } }, "trainer_advance": { "total": 691.8884773439697, "count": 63846, "self": 2.7936091670057976, "children": { "process_trajectory": { "total": 115.97346907896593, "count": 63846, "self": 115.63984853896585, "children": { "RLTrainer._checkpoint": { "total": 0.33362054000008357, "count": 2, "self": 0.33362054000008357 } } }, "_update_policy": { "total": 573.1213990979979, "count": 455, "self": 375.66337326101257, "children": { "TorchPPOOptimizer.update": { "total": 197.45802583698537, "count": 22803, "self": 197.45802583698537 } } } } } } }, "trainer_threads": { "total": 1.8810001165547874e-06, "count": 1, "self": 1.8810001165547874e-06 }, "TrainerController._save_models": { "total": 0.1599663399997553, "count": 1, "self": 0.0018834329998753674, "children": { "RLTrainer._checkpoint": { "total": 0.15808290699987992, "count": 1, "self": 0.15808290699987992 } } } } } } }