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

July 30, 2020 ยท Declared Dead ยท ๐Ÿ› Conference on Robot Learning

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Prasoon Goyal, Scott Niekum, Raymond J. Mooney arXiv ID 2007.15543 Category cs.LG: Machine Learning Cross-listed cs.AI, stat.ML Citations 60 Venue Conference on Robot Learning Last Checked 3 months ago
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 typically operate on structured representations of the environment, and/or assume some structure in the natural language commands. In this work, we propose a model that directly maps pixels to rewards, given a free-form natural language description of the task, which can then be used for policy learning. Our experiments on the Meta-World robot manipulation domain show that language-based rewards significantly improves the sample efficiency of policy learning, both in sparse and dense reward settings.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning

Died the same way โ€” ๐Ÿ‘ป Ghosted