Add Aloha env and ACT policy

WIP Aloha env tests pass

Rendering works (fps look fast tho? TODO action bounding is too wide [-1,1])

Update README

Copy past from act repo

Remove download.py add a WIP for Simxarm

Remove download.py add a WIP for Simxarm

Add act yaml (TODO: try train.py)

Training can runs (TODO: eval)

Add tasks without end_effector that are compatible with dataset, Eval can run (TODO: training and pretrained model)

Add AbstractEnv, Refactor AlohaEnv, Add rendering_hook in env, Minor modifications, (TODO: Refactor Pusht and Simxarm)

poetry lock

fix bug in compute_stats for action normalization

fix more bugs in normalization

fix training

fix import

PushtEnv inheriates AbstractEnv, Improve factory Normalization

Add _make_env to EnvAbstract

Add call_rendering_hooks to pusht env

SimxarmEnv inherites from AbstractEnv (NOT TESTED)

Add aloha tests artifacts + update pusht stats

fix image normalization: before env was in [0,1] but dataset in [0,255], and now both in [0,255]

Small fix on simxarm

Add next to obs

Add top camera to Aloha env (TODO: make it compatible with set of cameras)

Add top camera to Aloha env (TODO: make it compatible with set of cameras)

lerobot/scripts/eval.py

@@ -38,27 +38,18 @@ def eval_policy(
     successes = []
     threads = []
     for i in tqdm.tqdm(range(num_episodes)):
-        tensordict = env.reset()
-
         ep_frames = []
-
         if save_video or (return_first_video and i == 0):
 
-            def rendering_callback(env, td=None):
+            def render_frame(env):
                 ep_frames.append(env.render())  # noqa: B023
 
-            # render first frame before rollout
-            rendering_callback(env)
-        else:
-            rendering_callback = None
+            env.register_rendering_hook(render_frame)
 
         with torch.inference_mode():
             rollout = env.rollout(
                 max_steps=max_steps,
                 policy=policy,
-                callback=rendering_callback,
-                auto_reset=False,
-                tensordict=tensordict,
                 auto_cast_to_device=True,
             )
         # print(", ".join([f"{x:.3f}" for x in rollout["next", "reward"][:,0].tolist()]))
@@ -85,6 +76,8 @@ def eval_policy(
             if return_first_video and i == 0:
                 first_video = stacked_frames.transpose(0, 3, 1, 2)
 
+    env.reset_rendering_hooks()
+
     for thread in threads:
         thread.join()