policy

FYP-Using-LLMs-to-Generate-Reward-Functions-from-Natural-Language-in-RL-Environments

SamPlayz6 · PyTorch

or hover any field below to flag it

Overview

Name
FYP-Using-LLMs-to-Generate-Reward-Functions-from-Natural-Language-in-RL-Environments
Author
SamPlayz6
Framework
PyTorch
License
unknown
Skill type
other
Evidence level
untested
Task description
This research uses Large Language Models to generate reward functions from natural language in reinforcement learning. A flexible testbed evaluates these functions' accuracy, consistency, and robustness across various tasks and inputs, aiming to create an intuitive method for specifying RL rewards.

Spaces

Action space
other · 0-dim · 0Hz
Observation space
  • type: other

Links

HuggingFace repo
null
Paper (arXiv)
null

Compatible robots

3+17 mentioned but not in catalog yet

Compatible environments

0

No environments list FYP-Using-LLMs-to-Generate-Reward-Functions-from-Natural-Language-in-RL-Environments yet.

Datasets that reference this policy

0

No datasets reference FYP-Using-LLMs-to-Generate-Reward-Functions-from-Natural-Language-in-RL-Environments yet.