Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning.
Kaiwen WangRahul KidambiRyan SullivanAlekh AgarwalChristoph DannAndrea MichiMarco GelmiYunxuan LiRaghav GuptaAvinava DubeyAlexandre RaméJohan FerretGeoffrey CideronLe HouHongkun YuAmr AhmedAranyak MehtaLéonard HussenotOlivier BachemEdouard LeurentPublished in: CoRR (2024)
Keyphrases
- multi objective
- multi objective optimization
- evolutionary algorithm
- optimization algorithm
- multiobjective optimization
- genetic algorithm
- programming language
- particle swarm optimization
- multiple objectives
- objective function
- multi objective optimization problems
- language learning
- natural language
- pareto optimal
- nsga ii
- optimal policy
- trade off
- specification language
- bi objective
- evolutionary optimization
- multi objective evolutionary