| { | |
| "name": "root", | |
| "gauges": { | |
| "Pyramids.Policy.Entropy.mean": { | |
| "value": 0.2361476868391037, | |
| "min": 0.2354547381401062, | |
| "max": 1.4449989795684814, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Entropy.sum": { | |
| "value": 7061.76025390625, | |
| "min": 7061.76025390625, | |
| "max": 43835.48828125, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.mean": { | |
| "value": 989980.0, | |
| "min": 29942.0, | |
| "max": 989980.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Step.sum": { | |
| "value": 989980.0, | |
| "min": 29942.0, | |
| "max": 989980.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.mean": { | |
| "value": 0.364837110042572, | |
| "min": -0.0832914188504219, | |
| "max": 0.38894036412239075, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicValueEstimate.sum": { | |
| "value": 94.85765075683594, | |
| "min": -20.156522750854492, | |
| "max": 105.79177856445312, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.mean": { | |
| "value": 0.07150408625602722, | |
| "min": 0.05166880413889885, | |
| "max": 0.6241885423660278, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndValueEstimate.sum": { | |
| "value": 18.591062545776367, | |
| "min": 13.382220268249512, | |
| "max": 147.93267822265625, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.mean": { | |
| "value": 0.06877212627591625, | |
| "min": 0.063388971362396, | |
| "max": 0.07215767397469626, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.PolicyLoss.sum": { | |
| "value": 0.9628097678628276, | |
| "min": 0.476543673508347, | |
| "max": 1.072328270327382, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.mean": { | |
| "value": 0.012841389657477413, | |
| "min": 0.00028676849073964517, | |
| "max": 0.018203681996511314, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.ValueLoss.sum": { | |
| "value": 0.17977945520468377, | |
| "min": 0.0037279903796153873, | |
| "max": 0.2292331577108616, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.mean": { | |
| "value": 7.288190427778569e-06, | |
| "min": 7.288190427778569e-06, | |
| "max": 0.00029515063018788575, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.LearningRate.sum": { | |
| "value": 0.00010203466598889997, | |
| "min": 0.00010203466598889997, | |
| "max": 0.0036084399971866993, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.mean": { | |
| "value": 0.1024293642857143, | |
| "min": 0.1024293642857143, | |
| "max": 0.19838354285714285, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Epsilon.sum": { | |
| "value": 1.4340111000000002, | |
| "min": 1.3886848, | |
| "max": 2.5692822000000004, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.mean": { | |
| "value": 0.000252693492142857, | |
| "min": 0.000252693492142857, | |
| "max": 0.00983851593142857, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.Beta.sum": { | |
| "value": 0.0035377088899999983, | |
| "min": 0.0035377088899999983, | |
| "max": 0.12029104867000001, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.mean": { | |
| "value": 0.08153150230646133, | |
| "min": 0.07160131633281708, | |
| "max": 0.8177006840705872, | |
| "count": 33 | |
| }, | |
| "Pyramids.Losses.RNDLoss.sum": { | |
| "value": 1.141440987586975, | |
| "min": 1.0024183988571167, | |
| "max": 5.723904609680176, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.mean": { | |
| "value": 546.5370370370371, | |
| "min": 434.4166666666667, | |
| "max": 999.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.EpisodeLength.sum": { | |
| "value": 29513.0, | |
| "min": 16869.0, | |
| "max": 33460.0, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.mean": { | |
| "value": 1.1941221941400457, | |
| "min": -0.9997613410795888, | |
| "max": 1.3945110812783241, | |
| "count": 33 | |
| }, | |
| "Pyramids.Environment.CumulativeReward.sum": { | |
| "value": 64.48259848356247, | |
| "min": -30.992601573467255, | |
| "max": 98.71779828518629, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.mean": { | |
| "value": 1.1941221941400457, | |
| "min": -0.9997613410795888, | |
| "max": 1.3945110812783241, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.ExtrinsicReward.sum": { | |
| "value": 64.48259848356247, | |
| "min": -30.992601573467255, | |
| "max": 98.71779828518629, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.mean": { | |
| "value": 0.4326614055403129, | |
| "min": 0.35948275218308684, | |
| "max": 16.478979538468753, | |
| "count": 33 | |
| }, | |
| "Pyramids.Policy.RndReward.sum": { | |
| "value": 23.363715899176896, | |
| "min": 19.849750356937875, | |
| "max": 280.1426521539688, | |
| "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": "1730549767", | |
| "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]", | |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics", | |
| "mlagents_version": "1.2.0.dev0", | |
| "mlagents_envs_version": "1.2.0.dev0", | |
| "communication_protocol_version": "1.5.0", | |
| "pytorch_version": "2.5.0+cu121", | |
| "numpy_version": "1.23.5", | |
| "end_time_seconds": "1730552007" | |
| }, | |
| "total": 2240.018840874, | |
| "count": 1, | |
| "self": 0.47692465599948264, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.055652971999961665, | |
| "count": 1, | |
| "self": 0.055652971999961665 | |
| }, | |
| "TrainerController.start_learning": { | |
| "total": 2239.4862632460004, | |
| "count": 1, | |
| "self": 1.4196555140242708, | |
| "children": { | |
| "TrainerController._reset_env": { | |
| "total": 4.878029948000062, | |
| "count": 1, | |
| "self": 4.878029948000062 | |
| }, | |
| "TrainerController.advance": { | |
| "total": 2233.089691674976, | |
| "count": 63705, | |
| "self": 1.5250065640007051, | |
| "children": { | |
| "env_step": { | |
| "total": 1531.6885241019545, | |
| "count": 63705, | |
| "self": 1370.8834171189014, | |
| "children": { | |
| "SubprocessEnvManager._take_step": { | |
| "total": 159.9250046660169, | |
| "count": 63705, | |
| "self": 4.813720756955377, | |
| "children": { | |
| "TorchPolicy.evaluate": { | |
| "total": 155.1112839090615, | |
| "count": 62559, | |
| "self": 155.1112839090615 | |
| } | |
| } | |
| }, | |
| "workers": { | |
| "total": 0.8801023170361759, | |
| "count": 63705, | |
| "self": 0.0, | |
| "children": { | |
| "worker_root": { | |
| "total": 2234.4102480039946, | |
| "count": 63705, | |
| "is_parallel": true, | |
| "self": 985.7052809259508, | |
| "children": { | |
| "run_training.setup": { | |
| "total": 0.0, | |
| "count": 0, | |
| "is_parallel": true, | |
| "self": 0.0, | |
| "children": { | |
| "steps_from_proto": { | |
| "total": 0.002089568000087638, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0007007730000623269, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0013887950000253113, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0013887950000253113 | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 0.045694448999938686, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.0006429099998968013, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 0.00047442599998248625, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00047442599998248625 | |
| }, | |
| "communicator.exchange": { | |
| "total": 0.04294915499997387, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.04294915499997387 | |
| }, | |
| "steps_from_proto": { | |
| "total": 0.0016279580000855276, | |
| "count": 1, | |
| "is_parallel": true, | |
| "self": 0.00036739500012572535, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 0.0012605629999598023, | |
| "count": 8, | |
| "is_parallel": true, | |
| "self": 0.0012605629999598023 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "UnityEnvironment.step": { | |
| "total": 1248.7049670780439, | |
| "count": 63704, | |
| "is_parallel": true, | |
| "self": 33.72431849508666, | |
| "children": { | |
| "UnityEnvironment._generate_step_input": { | |
| "total": 23.972628711012476, | |
| "count": 63704, | |
| "is_parallel": true, | |
| "self": 23.972628711012476 | |
| }, | |
| "communicator.exchange": { | |
| "total": 1090.8120468829848, | |
| "count": 63704, | |
| "is_parallel": true, | |
| "self": 1090.8120468829848 | |
| }, | |
| "steps_from_proto": { | |
| "total": 100.19597298896008, | |
| "count": 63704, | |
| "is_parallel": true, | |
| "self": 20.90658750085629, | |
| "children": { | |
| "_process_rank_one_or_two_observation": { | |
| "total": 79.28938548810379, | |
| "count": 509632, | |
| "is_parallel": true, | |
| "self": 79.28938548810379 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_advance": { | |
| "total": 699.8761610090211, | |
| "count": 63705, | |
| "self": 2.75785383908476, | |
| "children": { | |
| "process_trajectory": { | |
| "total": 136.6855321009366, | |
| "count": 63705, | |
| "self": 136.42331249593667, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.26221960499992747, | |
| "count": 2, | |
| "self": 0.26221960499992747 | |
| } | |
| } | |
| }, | |
| "_update_policy": { | |
| "total": 560.4327750689997, | |
| "count": 458, | |
| "self": 315.50447419904003, | |
| "children": { | |
| "TorchPPOOptimizer.update": { | |
| "total": 244.92830086995968, | |
| "count": 22755, | |
| "self": 244.92830086995968 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| }, | |
| "trainer_threads": { | |
| "total": 1.1180000001331791e-06, | |
| "count": 1, | |
| "self": 1.1180000001331791e-06 | |
| }, | |
| "TrainerController._save_models": { | |
| "total": 0.09888499099997716, | |
| "count": 1, | |
| "self": 0.0014857279998068407, | |
| "children": { | |
| "RLTrainer._checkpoint": { | |
| "total": 0.09739926300017032, | |
| "count": 1, | |
| "self": 0.09739926300017032 | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } | |
| } |