Tech Meridian ← LIVE FEED
RU

RESEARCH · RESEARCH · #517

AALT: composition-aware active imitation learning that maximizes start-goal connectivity

The paper introduces Adaptive Agents via Latent Topologies (AALT), an active imitation-learning method that selects demonstrations to maximize expected gains in start–goal connectivity by organizing demonstrations into a topology of latent hub states and identifying high-value bridge demonstrations. In a simulated UR5e ordered-retrieval domain with 72 tasks, AALT raised success from 42/72 to 72/72 using only 3 additional demonstrations (5 transitions); after 20 demonstrations, the best baseline averaged 88.6% success using 98 transitions.

KEY POINTS

  1. The paper introduces Adaptive Agents via Latent Topologies (AALT), an active imitation-learning method that selects demonstrations to maximize expected gains in start–goal connectivity by organizing demonstrations into a topology of latent hub states and identifying high-value bridge demonstrations.
  2. In a simulated UR5e ordered-retrieval domain with 72 tasks, AALT raised success from 42/72 to 72/72 using only 3 additional demonstrations (5 transitions); after 20 demonstrations, the best baseline averaged 88.6% success using 98 transitions.
  3. By explicitly valuing compositional, bridge demonstrations and tying this objective to information gain about reachability, AALT can dramatically reduce required expert demonstrations for multi-start-goal task families.

WHY IT MATTERS

By explicitly valuing compositional, bridge demonstrations and tying this objective to information gain about reachability, AALT can dramatically reduce required expert demonstrations for multi-start-goal task families.

SOURCES & TIMELINE

1