PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards
arXiv:2007.15543
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.
arXiv commentConference on Robot Learning (CoRL), 2020
References in corpus (6)
- Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
- A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms
- From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following
- Learning to Understand Goal Specifications by Modelling Reward
- Beating Atari with Natural Language Guided Reinforcement Learning
- Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight