This project is used to embed the ltl tasks. This repo is built using bebbo-LTL2Action and LTL2Action
The repository implements training the embedding of LTL tasks through reinforcement learning executed on the LTLbootcamp environment. More details can be found in the Report.
or, for better compatibility, the following command can be used:
conda env create -f environment.yml
python pretrain.py
- Vaezipoor, Pashootan, Li, Andrew, Icarte, Rodrigo Toro, and McIlraith, Sheila (2021). “LTL2Action:Generalizing LTL Instructions for Multi-Task RL”. In:International Conference on MachineLearning (ICML)
- Icarte, Rodrigo Toro, Klassen, Toryn Q., Valenzano, Richard Anthony, and McIlraith, Sheila A.(2018). “Teaching Multiple Tasks to an RL Agent using LTL.” In:International Conferenceon Autonomous Agents and Multiagent. Systems (AAMAS), (pp. 452–461)
- Write code to evaluate the similarity among ltl tasks and evaluate the learnt embedding model.
- Construct the LLM model using langchain.
-
- Construct the model to generate similar ltl tasks and corresponding behaviors, and save them into possbible errors-revised task pairs. (done)
-
- Construct the embedding and use the retrieved content to construct the prompt. (done)
-
- Construct groundtruth dataset.
-
- How to build up robotic experiments to evaluate?
-