Timezone: »

 
Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning
Dhruv Shah · Ted Xiao · Alexander Toshev · Sergey Levine · brian ichter

@
in Deep Reinforcement Learning »
Event URL: https://openreview.net/forum?id=9FeG7u5Eirm »

Reinforcement learning can train policies that effectively perform complex tasks. However for long-horizon tasks, the performance of these methods degrades with horizon, often necessitating reasoning over and composing lower-level skills. Hierarchical reinforcement learning aims to enable this by providing a bank of low-level skills as action abstractions. Hierarchies can further improve on this by abstracting the space states as well. We posit that a suitable state abstraction should depend on the capabilities of the available lower-level policies. We propose Value Function Spaces: a simple approach that produces such a representation by using the value functions corresponding to each lower-level skill. These value functions capture the affordances of the scene, thus forming a representation that compactly abstracts task relevant information and robustly ignores distractors. Empirical evaluations for maze-solving and robotic manipulation tasks demonstrate that our approach improves long-horizon performance and enables better zero-shot generalization than alternative model-free and model-based methods.

Author Information

Dhruv Shah (None)
Ted Xiao (Google Brain)
Alexander Toshev (Google)
Sergey Levine (UC Berkeley)
brian ichter (Google)

More from the Same Authors