| β β | |
| βββ¬ββ‘ βββ¬ββ | |
| βββ¬ββββββ β¬ββββββ¬β | |
| ββ¬ββββββ¬β ββ¬βββββββ βββ | |
| β¬β¬β¬β¬ββββ¦β ββ¬ββββ£β£β£β¬ ββ£β£β¬ ββ£β£β£ βββ ββ£β£ | |
| β¬β¬β¬β¬β¬β¬β¬β¬βββ¬ββββ¬βͺβββ£β£β£β£β£β£β£β¬ ββ£β£β¬ ββ£β£β£ ββ£β£βββ£β£β£β β£β£β£ β£β£β£β£β£β£ ββ£β£β β£β£β£ | |
| β¬β¬β¬β¬β ββ¬β¬β¬β¬βββ£β£β£ββ β«β£β£β£β¬ ββ£β£β¬ ββ£β£β£ ββ£β£β£β ββ£β£β£ β£β£β£ βββ£β£ββ β«β£β£ ββ£β£ | |
| β¬β¬β¬β¬β ββ¬β¬β£β£ β«β£β£β£β¬ ββ£β£β¬ ββ£β£β£ ββ£β£β¬ β£β£β£ β£β£β£ ββ£β£ β£β£β£ββ£β£β | |
| β¬β¬β¬β β¬β¬β£β£ βββ£β£β¬ ββ£β£β£βββββ£β£β£β ββ£β£β¬ β£β£β£ β£β£β£ ββ£β£β¦β β£β£β£β£β£ | |
| β ββ¦β β¬β¬β£β£ ββββ βββ£β£β£β£ββ ββββ βββ βββ ββ£β£β£ ββ£β£β£ | |
| β©β¬β¬β¬β¬β¬β¬β¦β¦β¬β¬β£β£ββ£β£β£β£β£β£β£β β«β£β£β£β£ | |
| ββ¬β¬β¬β¬β¬β¬β¬β£β£β£β£β£β£ββ | |
| ββ¬β¬β¬β£β£β£β | |
| β | |
| Version information: | |
| ml-agents: 1.1.0, | |
| ml-agents-envs: 1.1.0, | |
| Communicator API: 1.5.0, | |
| PyTorch: 2.5.1+cu124 | |
| [INFO] Connected to Unity environment with package version 2.2.1-exp.1 and communication version 1.5.0 | |
| [INFO] Connected new brain: Pyramids?team=0 | |
| [INFO] Hyperparameters for behavior name Pyramids: | |
| trainer_type: ppo | |
| hyperparameters: | |
| batch_size: 128 | |
| buffer_size: 2048 | |
| learning_rate: 0.0003 | |
| beta: 0.01 | |
| epsilon: 0.2 | |
| lambd: 0.95 | |
| num_epoch: 3 | |
| shared_critic: False | |
| learning_rate_schedule: linear | |
| beta_schedule: linear | |
| epsilon_schedule: linear | |
| checkpoint_interval: 500000 | |
| network_settings: | |
| normalize: False | |
| hidden_units: 512 | |
| num_layers: 2 | |
| vis_encode_type: simple | |
| memory: None | |
| goal_conditioning_type: hyper | |
| deterministic: False | |
| reward_signals: | |
| extrinsic: | |
| gamma: 0.99 | |
| strength: 1.0 | |
| network_settings: | |
| normalize: False | |
| hidden_units: 128 | |
| num_layers: 2 | |
| vis_encode_type: simple | |
| memory: None | |
| goal_conditioning_type: hyper | |
| deterministic: False | |
| rnd: | |
| gamma: 0.99 | |
| strength: 0.01 | |
| network_settings: | |
| normalize: False | |
| hidden_units: 64 | |
| num_layers: 3 | |
| vis_encode_type: simple | |
| memory: None | |
| goal_conditioning_type: hyper | |
| deterministic: False | |
| learning_rate: 0.0001 | |
| encoding_size: None | |
| init_path: None | |
| keep_checkpoints: 5 | |
| even_checkpoints: False | |
| max_steps: 1500000 | |
| time_horizon: 128 | |
| summary_freq: 30000 | |
| threaded: False | |
| self_play: None | |
| behavioral_cloning: None | |
| [INFO] Pyramids. Step: 30000. Time Elapsed: 148.003 s. Mean Reward: -1.000. Std of Reward: 0.000. Training. | |
| [INFO] Pyramids. Step: 60000. Time Elapsed: 265.467 s. Mean Reward: -0.933. Std of Reward: 0.372. Training. | |
| [INFO] Pyramids. Step: 90000. Time Elapsed: 367.221 s. Mean Reward: -0.710. Std of Reward: 0.798. Training. | |
| [INFO] Pyramids. Step: 120000. Time Elapsed: 464.638 s. Mean Reward: -0.776. Std of Reward: 0.720. Training. | |
| [INFO] Pyramids. Step: 150000. Time Elapsed: 558.278 s. Mean Reward: -0.767. Std of Reward: 0.704. Training. | |
| [INFO] Pyramids. Step: 180000. Time Elapsed: 647.350 s. Mean Reward: -0.735. Std of Reward: 0.702. Training. | |
| [INFO] Pyramids. Step: 210000. Time Elapsed: 729.384 s. Mean Reward: -0.734. Std of Reward: 0.718. Training. | |
| [INFO] Pyramids. Step: 240000. Time Elapsed: 811.080 s. Mean Reward: -0.770. Std of Reward: 0.717. Training. | |
| [INFO] Pyramids. Step: 270000. Time Elapsed: 892.234 s. Mean Reward: -0.677. Std of Reward: 0.828. Training. | |
| [INFO] Pyramids. Step: 300000. Time Elapsed: 972.033 s. Mean Reward: -0.623. Std of Reward: 0.880. Training. | |
| [INFO] Pyramids. Step: 330000. Time Elapsed: 1052.993 s. Mean Reward: -0.547. Std of Reward: 0.933. Training. | |
| [INFO] Pyramids. Step: 360000. Time Elapsed: 1133.943 s. Mean Reward: -0.255. Std of Reward: 1.081. Training. | |
| [INFO] Pyramids. Step: 390000. Time Elapsed: 1214.047 s. Mean Reward: 0.361. Std of Reward: 1.218. Training. | |
| [INFO] Pyramids. Step: 420000. Time Elapsed: 1295.921 s. Mean Reward: 0.438. Std of Reward: 1.226. Training. | |
| [INFO] Pyramids. Step: 450000. Time Elapsed: 1379.688 s. Mean Reward: 0.412. Std of Reward: 1.220. Training. | |
| [INFO] Pyramids. Step: 480000. Time Elapsed: 1462.029 s. Mean Reward: 0.791. Std of Reward: 1.133. Training. | |
| [INFO] Exported ./results/Pyramids Training/Pyramids/Pyramids-499993.onnx | |
| [INFO] Pyramids. Step: 510000. Time Elapsed: 1548.600 s. Mean Reward: 1.152. Std of Reward: 0.981. Training. | |
| [INFO] Pyramids. Step: 540000. Time Elapsed: 1633.251 s. Mean Reward: 1.311. Std of Reward: 0.824. Training. | |
| [INFO] Pyramids. Step: 570000. Time Elapsed: 1721.782 s. Mean Reward: 1.343. Std of Reward: 0.833. Training. | |
| [INFO] Pyramids. Step: 600000. Time Elapsed: 1805.904 s. Mean Reward: 1.378. Std of Reward: 0.772. Training. | |
| [INFO] Pyramids. Step: 630000. Time Elapsed: 1893.478 s. Mean Reward: 1.566. Std of Reward: 0.591. Training. | |
| [INFO] Pyramids. Step: 660000. Time Elapsed: 1977.764 s. Mean Reward: 1.453. Std of Reward: 0.686. Training. | |
| [INFO] Pyramids. Step: 690000. Time Elapsed: 2066.482 s. Mean Reward: 1.632. Std of Reward: 0.319. Training. | |
| [INFO] Pyramids. Step: 720000. Time Elapsed: 2151.482 s. Mean Reward: 1.549. Std of Reward: 0.660. Training. | |
| [INFO] Pyramids. Step: 750000. Time Elapsed: 2240.531 s. Mean Reward: 1.592. Std of Reward: 0.536. Training. | |
| [INFO] Pyramids. Step: 780000. Time Elapsed: 2328.085 s. Mean Reward: 1.706. Std of Reward: 0.193. Training. | |
| [INFO] Pyramids. Step: 810000. Time Elapsed: 2411.292 s. Mean Reward: 1.578. Std of Reward: 0.580. Training. | |
| [INFO] Pyramids. Step: 840000. Time Elapsed: 2501.359 s. Mean Reward: 1.682. Std of Reward: 0.335. Training. | |
| [INFO] Pyramids. Step: 870000. Time Elapsed: 2586.919 s. Mean Reward: 1.659. Std of Reward: 0.333. Training. | |
| [INFO] Pyramids. Step: 900000. Time Elapsed: 2680.870 s. Mean Reward: 1.629. Std of Reward: 0.434. Training. | |
| [INFO] Pyramids. Step: 930000. Time Elapsed: 2767.200 s. Mean Reward: 1.597. Std of Reward: 0.560. Training. | |
| [INFO] Pyramids. Step: 960000. Time Elapsed: 2857.335 s. Mean Reward: 1.724. Std of Reward: 0.166. Training. | |
| [INFO] Pyramids. Step: 990000. Time Elapsed: 2941.618 s. Mean Reward: 1.619. Std of Reward: 0.553. Training. | |
| [INFO] Exported ./results/Pyramids Training/Pyramids/Pyramids-999946.onnx | |
| [INFO] Pyramids. Step: 1020000. Time Elapsed: 3028.674 s. Mean Reward: 1.678. Std of Reward: 0.411. Training. | |
| [INFO] Pyramids. Step: 1050000. Time Elapsed: 3118.122 s. Mean Reward: 1.692. Std of Reward: 0.402. Training. | |
| [INFO] Pyramids. Step: 1080000. Time Elapsed: 3216.680 s. Mean Reward: 1.727. Std of Reward: 0.183. Training. | |
| [INFO] Pyramids. Step: 1110000. Time Elapsed: 3311.014 s. Mean Reward: 1.661. Std of Reward: 0.489. Training. | |
| [INFO] Pyramids. Step: 1140000. Time Elapsed: 3403.759 s. Mean Reward: 1.660. Std of Reward: 0.528. Training. | |
| [INFO] Pyramids. Step: 1170000. Time Elapsed: 3502.028 s. Mean Reward: 1.663. Std of Reward: 0.472. Training. | |
| [INFO] Pyramids. Step: 1200000. Time Elapsed: 3593.599 s. Mean Reward: 1.724. Std of Reward: 0.368. Training. | |
| [INFO] Pyramids. Step: 1230000. Time Elapsed: 3696.908 s. Mean Reward: 1.726. Std of Reward: 0.294. Training. | |
| [INFO] Pyramids. Step: 1260000. Time Elapsed: 3794.103 s. Mean Reward: 1.698. Std of Reward: 0.393. Training. | |
| [INFO] Pyramids. Step: 1290000. Time Elapsed: 3880.079 s. Mean Reward: 1.725. Std of Reward: 0.296. Training. | |
| [INFO] Pyramids. Step: 1320000. Time Elapsed: 3962.680 s. Mean Reward: 1.721. Std of Reward: 0.297. Training. | |
| [INFO] Pyramids. Step: 1350000. Time Elapsed: 4045.175 s. Mean Reward: 1.770. Std of Reward: 0.140. Training. | |
| [INFO] Pyramids. Step: 1380000. Time Elapsed: 4137.379 s. Mean Reward: 1.735. Std of Reward: 0.287. Training. | |
| [INFO] Pyramids. Step: 1410000. Time Elapsed: 4225.323 s. Mean Reward: 1.680. Std of Reward: 0.395. Training. | |
| [INFO] Pyramids. Step: 1440000. Time Elapsed: 4312.635 s. Mean Reward: 1.731. Std of Reward: 0.297. Training. | |
| [INFO] Pyramids. Step: 1470000. Time Elapsed: 4398.072 s. Mean Reward: 1.720. Std of Reward: 0.380. Training. | |
| [INFO] Pyramids. Step: 1500000. Time Elapsed: 4495.374 s. Mean Reward: 1.770. Std of Reward: 0.128. Training. | |
| [INFO] Exported ./results/Pyramids Training/Pyramids/Pyramids-1499929.onnx | |
| [INFO] Exported ./results/Pyramids Training/Pyramids/Pyramids-1500057.onnx | |
| [INFO] Copied ./results/Pyramids Training/Pyramids/Pyramids-1500057.onnx to ./results/Pyramids Training/Pyramids.onnx. | |