Sub-Goal Trees -- a Framework for Goal-Based Reinforcement Learning
Jurgenson, Tom, Avner, Or, Groshev, Edward, Tamar, Aviv
–arXiv.org Artificial Intelligence
Many AI problems, in robotics and other domains, are goal-based, essentially seeking trajectories leading to various goal states. Reinforcement learning (RL), building on Bellman's optimality equation, naturally optimizes for a single goal, yet can be made multi-goal by augmenting the state with the goal. Instead, we propose a new RL framework, derived from a dynamic programming equation for the all pairs shortest path (APSP) problem, which naturally solves multi-goal queries. We show that this approach has computational benefits for both standard and approximate dynamic programming. Interestingly, our formulation prescribes a novel protocol for computing a trajectory: instead of predicting the next state given its predecessor, as in standard RL, a goal-conditioned trajectory is constructed by first predicting an intermediate state between start and goal, partitioning the trajectory into two. Then, recursively, predicting intermediate points on each sub-segment, until a complete trajectory is obtained. We call this trajectory structure a sub-goal tree. Building on it, we additionally extend the policy gradient methodology to recursively predict sub-goals, resulting in novel goal-based algorithms. Finally, we apply our method to neural motion planning, where we demonstrate significant improvements compared to standard RL on navigating a 7-DoF robot arm between obstacles.
arXiv.org Artificial Intelligence
Feb-27-2020
- Genre:
- Research Report (0.64)
- Technology:
- Information Technology > Artificial Intelligence
- Cognitive Science > Problem Solving (1.00)
- Machine Learning > Reinforcement Learning (1.00)
- Representation & Reasoning (1.00)
- Robots (1.00)
- Information Technology > Artificial Intelligence