jackyliang42 commited on
Commit
117bf34
·
1 Parent(s): fc126c5

updated readme

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -11,13 +11,17 @@ license: apache-2.0
11
  ---
12
 
13
  # Code as Policies Tabletop Manipulation Interactive Demo
 
14
  This notebook is a part of the open-source code release associated with the paper:
 
15
  [Code as Policies: Language Model Programs for Embodied Control](https://code-as-policies.github.io/)
 
16
  This notebook gives an interactive demo for the simulated tabletop manipulation domain, seen in the paper section IV.D
17
 
18
  ## Preparations
19
  1. Obtain an [OpenAI API Key](https://openai.com/blog/openai-api/)
20
- 2. Gain Codex access by [joining the waitlist](https://openai.com/blog/openai-codex/)
 
21
  Once you have Codex access you can use `code-davinci-002`. Using the GPT-3 model (`text-dainvci-002`) is also ok, but performance won't be as good (there will be more code logic errors).
22
 
23
  ## Usage
 
11
  ---
12
 
13
  # Code as Policies Tabletop Manipulation Interactive Demo
14
+
15
  This notebook is a part of the open-source code release associated with the paper:
16
+
17
  [Code as Policies: Language Model Programs for Embodied Control](https://code-as-policies.github.io/)
18
+
19
  This notebook gives an interactive demo for the simulated tabletop manipulation domain, seen in the paper section IV.D
20
 
21
  ## Preparations
22
  1. Obtain an [OpenAI API Key](https://openai.com/blog/openai-api/)
23
+ 2. Gain Codex access by [joining the waitlist](https://openai.com/blog/openai-codex/)
24
+
25
  Once you have Codex access you can use `code-davinci-002`. Using the GPT-3 model (`text-dainvci-002`) is also ok, but performance won't be as good (there will be more code logic errors).
26
 
27
  ## Usage