llm-pddl's People
Forkers
codeaudit patrickmcguinness mistobaan atlas3dss nashid bpshaver danwalls75 tellieengineering ckqqqq eltociear jaytoday ai-natural-language-processing-lab cat-stack-boop jjhw evelynmitchell jxzhangjhu jakderrida bellyfat tynguyen kkaay0708 junjungoal viprob-ai shaotujia alexanderdurr yuqianjiang krishpavan keke-220 zhenyu818 rpatil524 mayi140611 aemartinezllm-pddl's Issues
Downloading downward
When I was downloading downward as the instructions in the document Assignment 1
I first clone the repository
then run ./build.py
but I met problem in this process
`Building configuration release.
Executing command "cmake -G Unix Makefiles -DCMAKE_BUILD_TYPE=Release ../../src" in directory "./builds/release".
-- Building for 64-bit.
CMake Error at cmake_modules/FastDownwardMacros.cmake:7 (message):
/usr/bin/c++ does not support -std=c++20
Call Stack (most recent call first):
cmake_modules/FastDownwardMacros.cmake:18 (check_and_set_compiler_flag)
search/CMakeLists.txt:25 (fast_downward_set_compiler_flags)
-- Configuring incomplete, errors occurred!
See also "/home/qjx/downward/builds/release/CMakeFiles/CMakeOutput.log".
See also "/home/qjx/downward/builds/release/CMakeFiles/CMakeError.log".
Traceback (most recent call last):
File "./build.py", line 149, in
main()
File "./build.py", line 145, in main
build(config_name, CONFIGS[config_name], make_parameters)
File "./build.py", line 121, in build
cwd=build_path)
File "./build.py", line 98, in try_run
subprocess.check_call(cmd, cwd=cwd)
File "/opt/conda/lib/python3.7/subprocess.py", line 363, in check_call
raise CalledProcessError(retcode, cmd)
subprocess.CalledProcessError: Command '['cmake', '-G', 'Unix Makefiles', '-DCMAKE_BUILD_TYPE=Release', '../../src']' returned non-zero exit status 1.`
Ground-truth Problem PDDL Generation
Hi, May I ask how did you generate the ground-truth Problem PDDL for each task in each domain? Could you provide any scripts?
Thank you!
Question about validation.
Hi, thanks for sharing the great work.
I am wondering how to calculate the success rate reported in the paper. Since I ran the validation program in the floortile domain and get the result of 6 plans valid in run1, 6 in run2, and 6 in run3. I am wondering how to get the 53.3% result reported in the paper.
Moreover, may I ask how to evaluate the success rate of plans generated by other baseline methods? The validation file only contains evaluations in the LLM+P-ic method.
Thanks for your patience and I am really looking forward to your reply.
Cleaning LLM-generated pddl problem files
Thanks for the nice work!
I am wondering when you use LLM to generate pddl problem files, how do you handle the cleaning, i.e. removing the extra text other than pddl file. I have tried several LLM models and the pddl problem files would contain other text.
Request: add formatted bibtex cite for associated paper
make it easy for us to cite https://arxiv.org/abs/2304.11477 :)
run validate.py
How to run the validate.py file under this folder? There is an error message 'No such file or directory: ./' when running. downward/validate'ใ
Tidy-Up
Hi,
How was the tidy-up ground-truth PDDL generated/made? Also, can you please provide it along with the related files in this repo?
Thanks
How can I generate more data instances?
valid problem
when running validate_plans.py
I got FileNotFoundError: [Errno 2] No such file or directory: './downward/validate'
gould you please update a complete instruction on validating?
PDDL parser
In: domains/blocksworld/description_generator.py
There's an import:
from pddl_parser import pddl_file
Can you please specify how to obtain pddl_parser?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.