Learning from Demonstrations via Capability-Aware Goal Sampling

TL;DR

Cago is a novel imitation learning method that adaptively selects intermediate goals based on the agent's current capabilities, leading to improved sample efficiency and performance in long-horizon, goal-conditioned tasks.

Contribution

Cago introduces a capability-aware goal sampling approach that dynamically guides learning by selecting goals just beyond the agent's current reach, enhancing imitation learning robustness.

Findings

Cago outperforms existing methods in sample efficiency.

Cago achieves higher final performance across various tasks.

Cago effectively handles sparse rewards and long horizons.

Abstract

Despite its promise, imitation learning often fails in long-horizon environments where perfect replication of demonstrations is unrealistic and small errors can accumulate catastrophically. We introduce Cago (Capability-Aware Goal Sampling), a novel learning-from-demonstrations method that mitigates the brittle dependence on expert trajectories for direct imitation. Unlike prior methods that rely on demonstrations only for policy initialization or reward shaping, Cago dynamically tracks the agent's competence along expert trajectories and uses this signal to select intermediate steps--goals that are just beyond the agent's current reach--to guide learning. This results in an adaptive curriculum that enables steady progress toward solving the full task. Empirical results demonstrate that Cago significantly improves sample efficiency and final performance across a range of sparse-reward, goal-conditioned tasks, consistently outperforming existing learning from-demonstrations baselines.