Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning
arXiv:2111.03189
Abstract
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 chaining 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.
Accepted to ICLR 2022
References in corpus (8)
- Rainbow: Combining Improvements in Deep Reinforcement Learning
- Reinforcement Learning with Unsupervised Auxiliary Tasks
- Soft Actor-Critic for Discrete Action Settings
- Loss is its own Reward: Self-Supervision for Reinforcement Learning
- BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning
- MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale
- Hierarchical Reinforcement Learning By Discovering Intrinsic Options
- Affordance as general value function: A computational model