lianganimation commited on
Commit
f7fd08d
·
verified ·
1 Parent(s): ee701d3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -2
README.md CHANGED
@@ -5,6 +5,8 @@ pipeline_tag: robotics
5
 
6
  # TokenHSI Checkpoint Instruction
7
 
 
 
8
  Please download the checkpoints and organize them as the following file structure:
9
 
10
  ```
@@ -27,9 +29,11 @@ Please download the checkpoints and organize them as the following file structur
27
  |-- ckpt_stage2_comp_traj_carry
28
  |-- ckpt_stage2_comp_sit_carry
29
  |-- ckpt_stage2_comp_climb_carry
 
 
 
 
30
  |-- ckpt_stage2_longterm.pth
31
- |-- ...
32
- |-- (more models are coming soon!)
33
  ```
34
 
35
  * We first provide four single-task environments, including path-following, sitting, climbing, and carrying. For each task, we train a specialized policy using AMP. The trained models are:
 
5
 
6
  # TokenHSI Checkpoint Instruction
7
 
8
+ [2025-04-06] All models have been released!
9
+
10
  Please download the checkpoints and organize them as the following file structure:
11
 
12
  ```
 
29
  |-- ckpt_stage2_comp_traj_carry
30
  |-- ckpt_stage2_comp_sit_carry
31
  |-- ckpt_stage2_comp_climb_carry
32
+ |-- ckpt_stage2_objShape_chair.pth
33
+ |-- ckpt_stage2_objShape_table.pth
34
+ |-- ckpt_stage2_terrainShape_traj.pth
35
+ |-- ckpt_stage2_terrainShape_carry.pth
36
  |-- ckpt_stage2_longterm.pth
 
 
37
  ```
38
 
39
  * We first provide four single-task environments, including path-following, sitting, climbing, and carrying. For each task, we train a specialized policy using AMP. The trained models are: