Improves policy behavior of Franka Cabinet and Allegro (#111)

# Description

Improves policy behavior for training Franka Cabinet direct environment
and Repose Cube Allegro direct environments.

## Type of change

- Bug fix (non-breaking change which fixes an issue)

## Checklist

- [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with
`./isaaclab.sh --format`
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have updated the changelog and the corresponding version in the
extension's `config/extension.toml` file
- [ ] I have added my name to the `CONTRIBUTORS.md` or my name already
exists there

<!--
As you go through the checklist above, you can mark something as done by
putting an x character in it

For example,
- [x] I have done this task
- [ ] I have not done this task
-->

source/extensions/omni.isaac.lab/omni/isaac/lab/sensors/camera/tiled_camera.py

@@ -24,7 +24,7 @@ from ..sensor_base import SensorBase
 from .camera import Camera
 
 if TYPE_CHECKING:
-    from .camera_cfg import TiledCameraCfg
+    from .tiled_camera_cfg import TiledCameraCfg
 
 
 class TiledCamera(Camera):

source/extensions/omni.isaac.lab_tasks/omni/isaac/lab_tasks/direct/allegro_hand/agents/rl_games_ppo_cfg.yaml

@@ -30,7 +30,7 @@ params:
           val: 0
         fixed_sigma: True
     mlp:
-      units: [512, 512, 256, 128]
+      units: [1024, 512, 256, 128]
       activation: elu
       d2rl: False
 

source/extensions/omni.isaac.lab_tasks/omni/isaac/lab_tasks/direct/allegro_hand/agents/rsl_rl_ppo_cfg.py

@@ -21,8 +21,8 @@ class AllegroHandPPORunnerCfg(RslRlOnPolicyRunnerCfg):
     empirical_normalization = True
     policy = RslRlPpoActorCriticCfg(
         init_noise_std=1.0,
-        actor_hidden_dims=[512, 512, 256, 128],
-        critic_hidden_dims=[512, 512, 256, 128],
+        actor_hidden_dims=[1024, 512, 256, 128],
+        critic_hidden_dims=[1024, 512, 256, 128],
         activation="elu",
     )
     algorithm = RslRlPpoAlgorithmCfg(

source/extensions/omni.isaac.lab_tasks/omni/isaac/lab_tasks/direct/allegro_hand/allegro_hand_env_cfg.py

@@ -112,7 +112,7 @@ class AllegroHandEnvCfg(DirectRLEnvCfg):
     fall_penalty = 0
     fall_dist = 0.24
     vel_obs_scale = 0.2
-    success_tolerance = 0.1
+    success_tolerance = 0.2
     max_consecutive_success = 0
     av_factor = 0.1
     act_moving_average = 1.0