Combining Q-Learning and Search with Amortized Value Estimates
This addresses the challenge of computational cost and performance trade-offs in reinforcement learning for researchers and practitioners, offering an incremental improvement by integrating existing methods.
The paper tackled the problem of combining model-free Q-learning with model-based Monte-Carlo Tree Search (MCTS) to improve efficiency and performance in reinforcement learning tasks. The result was the SAVE approach, which consistently achieved higher rewards with fewer training steps and strong performance with very small search budgets, as demonstrated on physical reasoning tasks and Atari.
We introduce "Search with Amortized Value Estimates" (SAVE), an approach for combining model-free Q-learning with model-based Monte-Carlo Tree Search (MCTS). In SAVE, a learned prior over state-action values is used to guide MCTS, which estimates an improved set of state-action values. The new Q-estimates are then used in combination with real experience to update the prior. This effectively amortizes the value computation performed by MCTS, resulting in a cooperative relationship between model-free learning and model-based search. SAVE can be implemented on top of any Q-learning agent with access to a model, which we demonstrate by incorporating it into agents that perform challenging physical reasoning tasks and Atari. SAVE consistently achieves higher rewards with fewer training steps, and---in contrast to typical model-based search approaches---yields strong performance with very small search budgets. By combining real experience with information computed during search, SAVE demonstrates that it is possible to improve on both the performance of model-free learning and the computational cost of planning.