Human-Inspired Multi-Level Reinforcement Learning

Reinforcement learning (RL), a common tool in decision making, learns control policies from various experiences based on the associated cumulative return/rewards without treating them differently. Humans, on the contrary, often learn to distinguish from discrete levels of performance and extract the underlying insights/information (beyond reward signals) towards their decision optimization. For instance, when learning to play tennis, a human player does not treat all unsuccessful attempts equally. Missing the ball completely signals a more severe mistake than hitting it out of bounds (although the cumulative rewards can be similar for both cases). Learning effectively from multi-level experiences is essential in human decision making. This motivates us to develop a novel multi-level RL method that learns from multi-level experiences via extracting multi-level information. At the low level of information extraction, we utilized the existing rating-based reinforcement learning to infer inherent reward signals that illustrate the value of states or state-action pairs accordingly. At the high level of information extraction, we propose to extract important directional information from different-level experiences so that policies can be updated towards desired deviation from these different levels of experiences. Specifically, we propose a new policy loss function that penalizes distribution similarities between the current policy and different-level experiences, and assigns different weights to the penalty terms based on the performance levels. Furthermore, the integration of the two levels towards multi-level RL guides the agent toward policy improvements that benefit both reward improvement and policy improvement, hence yielding a similar learning mechanism as humans. To evaluate the effectiveness of the proposed method, we present results for experiments on a few typical environments that show its advantages over the existing rating-based reinforcement learning, where a single reward learning was used.