Language-Conditioned Goal Generation: a New Approach to Language Grounding for RL
arXiv:2006.07043
Abstract
In the real world, linguistic agents are also embodied agents: they perceive and act in the physical world. The notion of Language Grounding questions the interactions between language and embodiment: how do learning agents connect or ground linguistic representations to the physical world ? This question has recently been approached by the Reinforcement Learning community under the framework of instruction-following agents. In these agents, behavioral policies or reward functions are conditioned on the embedding of an instruction expressed in natural language. This paper proposes another approach: using language to condition goal generators. Given any goal-conditioned policy, one could train a language-conditioned goal generator to generate language-agnostic goals for the agent. This method allows to decouple sensorimotor learning from language acquisition and enable agents to demonstrate a diversity of behaviors for any given instruction. We propose a particular instantiation of this approach and demonstrate its benefits.
References in corpus (13)
- Illuminating search spaces by mapping elites
- Hindsight Experience Replay
- Visual Reinforcement Learning with Imagined Goals
- Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
- Grounded Language Learning in a Simulated 3D World
- Curiosity Driven Exploration of Learned Disentangled Goal Spaces
- Learning to Understand Goal Specifications by Modelling Reward
- Skew-Fit: State-Covering Self-Supervised Reinforcement Learning
- Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration
- Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration
- Automated curricula through setter-solver interactions
- ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning
- Language is Power: Representing States Using Natural Language in Reinforcement Learning