Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning
This addresses the problem of policy learning in complex offline RL settings, especially for environments with sparse rewards and long horizons, and is incremental as it builds on existing world model and graph-based approaches.
The paper tackles the difficulty of learning policies in complex environments with continuous state-action spaces, sparse rewards, and long temporal horizons by building a simple, discrete world model called Value Memory Graph (VMG) for offline RL, and experiments on the D4RL benchmark show that VMG outperforms state-of-the-art methods in several goal-oriented tasks.
Reinforcement Learning (RL) methods are typically applied directly in environments to learn policies. In some complex environments with continuous state-action spaces, sparse rewards, and/or long temporal horizons, learning a good policy in the original environments can be difficult. Focusing on the offline RL setting, we aim to build a simple and discrete world model that abstracts the original environment. RL methods are applied to our world model instead of the environment data for simplified policy learning. Our world model, dubbed Value Memory Graph (VMG), is designed as a directed-graph-based Markov decision process (MDP) of which vertices and directed edges represent graph states and graph actions, separately. As state-action spaces of VMG are finite and relatively small compared to the original environment, we can directly apply the value iteration algorithm on VMG to estimate graph state values and figure out the best graph actions. VMG is trained from and built on the offline RL dataset. Together with an action translator that converts the abstract graph actions in VMG to real actions in the original environment, VMG controls agents to maximize episode returns. Our experiments on the D4RL benchmark show that VMG can outperform state-of-the-art offline RL methods in several goal-oriented tasks, especially when environments have sparse rewards and long temporal horizons. Code is available at https://github.com/TsuTikgiau/ValueMemoryGraph