Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction
This addresses computational bottlenecks in offline reinforcement learning for robotics and control applications, though it is an incremental improvement combining existing techniques like VQ-VAE and MCTS.
The paper tackles the challenge of sequential decision-making in high-dimensional continuous action spaces in stochastic environments by introducing the Latent Macro Action Planner (L-MAP), which learns temporally extended macro-actions to reduce action dimensionality and uses Monte Carlo tree search for planning, resulting in performance on-par with strong model-free baselines in tasks like continuous control and robotic hand manipulation.
Sequential decision-making in high-dimensional continuous action spaces, particularly in stochastic environments, faces significant computational challenges. We explore this challenge in the traditional offline RL setting, where an agent must learn how to make decisions based on data collected through a stochastic behavior policy. We present Latent Macro Action Planner (L-MAP), which addresses this challenge by learning a set of temporally extended macro-actions through a state-conditional Vector Quantized Variational Autoencoder (VQ-VAE), effectively reducing action dimensionality. L-MAP employs a (separate) learned prior model that acts as a latent transition model and allows efficient sampling of plausible actions. During planning, our approach accounts for stochasticity in both the environment and the behavior policy by using Monte Carlo tree search (MCTS). In offline RL settings, including stochastic continuous control tasks, L-MAP efficiently searches over discrete latent actions to yield high expected returns. Empirical results demonstrate that L-MAP maintains low decision latency despite increased action dimensionality. Notably, across tasks ranging from continuous control with inherently stochastic dynamics to high-dimensional robotic hand manipulation, L-MAP significantly outperforms existing model-based methods and performs on-par with strong model-free actor-critic baselines, highlighting the effectiveness of the proposed approach in planning in complex and stochastic environments with high-dimensional action spaces.