AILGNCAug 15, 2023

Sophisticated Learning: A novel algorithm for active learning during model-based planning

arXiv:2308.08029v2h-index: 4
AI Analysis

This work addresses decision-making under radical uncertainty for biologically inspired AI agents, representing an incremental improvement over existing methods.

The authors tackled the problem of decision-making under uncertainty by introducing Sophisticated Learning (SL), a planning-to-learn algorithm that embeds active parameter learning within the Sophisticated Inference framework, and found that in a seasonal foraging task, SL agents survived 8.2% longer than SI and 35% longer than Bayes-adaptive Reinforcement Learning in early trials, with SL reaching convergence 40% faster than SI.

We introduce Sophisticated Learning (SL), a planning-to-learn algorithm that embeds active parameter learning inside the Sophisticated Inference (SI) tree-search framework of Active Inference. Unlike SI -- which optimizes beliefs about hidden states -- SL also updates beliefs about model parameters within each simulated branch, enabling counterfactual reasoning about how future observations would improve subsequent planning. We compared SL with Bayes-adaptive Reinforcement Learning (BARL) agents as well as with its parent algorithm, SI. Using a biologically inspired seasonal foraging task in which resources shift probabilistically over a 10x10 grid, we designed experiments that forced agents to balance probabilistic reward harvesting against information gathering. In early trials, where rapid learning is vital, SL agents survive, on average, 8.2% longer than SI and 35% longer than Bayes-adaptive Reinforcement Learning. While both SL and SI showed equal convergence performance, SL reached this convergence 40% faster than SI. Additionally, SL showed robust out-performance of other algorithms in altered environment configurations. Our results show that incorporating active learning into multi-step planning materially improves decision making under radical uncertainty, and reinforces the broader utility of Active Inference for modeling biologically relevant behavior.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes