Exploratory Gradient Boosting for Reinforcement Learning in Complex Domains
This work addresses scaling reinforcement learning to real-world domains with high-dimensional inputs, though it appears incremental as it combines existing ideas like gradient boosting and state abstraction.
The paper tackled the challenges of high-dimensional observations and complex dynamics in reinforcement learning by introducing a gradient-boosting function approximator and an exploration strategy, achieving competitive performance on standard tasks and substantial improvements over baselines on new high-dimensional Minecraft benchmarks.
High-dimensional observations and complex real-world dynamics present major challenges in reinforcement learning for both function approximation and exploration. We address both of these challenges with two complementary techniques: First, we develop a gradient-boosting style, non-parametric function approximator for learning on $Q$-function residuals. And second, we propose an exploration strategy inspired by the principles of state abstraction and information acquisition under uncertainty. We demonstrate the empirical effectiveness of these techniques, first, as a preliminary check, on two standard tasks (Blackjack and $n$-Chain), and then on two much larger and more realistic tasks with high-dimensional observation spaces. Specifically, we introduce two benchmarks built within the game Minecraft where the observations are pixel arrays of the agent's visual field. A combination of our two algorithmic techniques performs competitively on the standard reinforcement-learning tasks while consistently and substantially outperforming baselines on the two tasks with high-dimensional observation spaces. The new function approximator, exploration strategy, and evaluation benchmarks are each of independent interest in the pursuit of reinforcement-learning methods that scale to real-world domains.