Graph-based RL agents can solve logic puzzles larger than anything seen in training, with graph structure, reward design, and recurrence each changing how far extrapolation goes.
PUZZLES: A Benchmark for Neural Algorithmic Reasoning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Algorithmic reasoning is a fundamental cognitive ability that plays a pivotal role in problem-solving and decision-making processes. Reinforcement Learning (RL) has demonstrated remarkable proficiency in tasks such as motor control, handling perceptual input, and managing stochastic environments. These advancements have been enabled in part by the availability of benchmarks. In this work we introduce PUZZLES, a benchmark based on Simon Tatham's Portable Puzzle Collection, aimed at fostering progress in algorithmic and logical reasoning in RL. PUZZLES contains 40 diverse logic puzzles of adjustable sizes and varying levels of complexity; many puzzles also feature a diverse set of additional configuration parameters. The 40 puzzles provide detailed information on the strengths and generalization capabilities of RL agents. Furthermore, we evaluate various RL algorithms on PUZZLES, providing baseline comparisons and demonstrating the potential for future research. All the software, including the environment, is available at https://github.com/ETH-DISCO/rlp.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beyond Interpolation: Extrapolative Reasoning with Reinforcement Learning and Graph Neural Networks
Graph-based RL agents can solve logic puzzles larger than anything seen in training, with graph structure, reward design, and recurrence each changing how far extrapolation goes.