PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards

Prasoon Goyal
Prasoon Goyal
Scott Niekum
Scott Niekum
Cited by: 0|Bibtex|Views10
Other Links: arxiv.org

Abstract:

Reinforcement learning (RL), particularly in sparse reward settings, often requires prohibitively large numbers of interactions with the environment, thereby limiting its applicability to complex problems. To address this, several prior approaches have used natural language to guide the agent's exploration. However, these approaches typ...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments