ExTra: Transfer-guided Exploration
This work addresses the challenge of efficient exploration in reinforcement learning, particularly for tasks with sparse rewards, by leveraging prior knowledge from similar tasks, though it is incremental as it builds on existing exploration methods.
The paper tackles the problem of exploration in reinforcement learning by introducing a transfer-guided approach that uses an optimal policy from a related task to guide action selection, demonstrating improved convergence rates over several domain-specific exploration strategies in gridworld environments.
In this work we present a novel approach for transfer-guided exploration in reinforcement learning that is inspired by the human tendency to leverage experiences from similar encounters in the past while navigating a new task. Given an optimal policy in a related task-environment, we show that its bisimulation distance from the current task-environment gives a lower bound on the optimal advantage of state-action pairs in the current task-environment. Transfer-guided Exploration (ExTra) samples actions from a Softmax distribution over these lower bounds. In this way, actions with potentially higher optimum advantage are sampled more frequently. In our experiments on gridworld environments, we demonstrate that given access to an optimal policy in a related task-environment, ExTra can outperform popular domain-specific exploration strategies viz. epsilon greedy, Model-Based Interval Estimation - Exploration Bonus (MBIE-EB), Pursuit and Boltzmann in rate of convergence. We further show that ExTra is robust to choices of source task and shows a graceful degradation of performance as the dissimilarity of the source task increases. We also demonstrate that ExTra, when used alongside traditional exploration algorithms, improves their rate of convergence. Thus it is capable of complementing the efficacy of traditional exploration algorithms.