Dongjae Kim

Wonseo Jang, Dongjae Kim

Deep reinforcement learning (RL) models, despite their efficiency in learning an optimal policy in static environments, easily loses previously learned knowledge (i.e., catastrophic forgetting). It leads RL models to poor performance in continual reinforcement learning (CRL) scenarios. To address this, we present an arbitration control mechanism over an ensemble of RL agents. It is motivated by and closely aligned with how humans make decisions in a CRL context using an arbitration control of multiple RL agents in parallel as observed in the prefrontal cortex. We integrated two key ideas into our model: (1) an ensemble of RLs (i.e., DQN variants) explicitly trained to have diverse value functions and (2) an arbitration control that prioritizes agents with higher reliability (i.e., less error) in recent trials. We propose a framework for CRL, an Arbitration Control for an Ensemble of Diversified DQN variants (ACED-DQN). We demonstrate significant performance improvements in both static and continual environments, supported by empirical evidence showing the effectiveness of arbitration control over diversified DQNs during training. In this work, we introduced a framework that enables RL agents to continuously learn, with inspiration from the human brain.

Dongjae Kim, Jee Hang Lee, Jae Hoon Shin et al.

Although deep RL models have shown a great potential for solving various types of tasks with minimal supervision, several key challenges remain in terms of learning from limited experience, adapting to environmental changes, and generalizing learning from a single task. Recent evidence in decision neuroscience has shown that the human brain has an innate capacity to resolve these issues, leading to optimism regarding the development of neuroscience-inspired solutions toward sample-efficient, and generalizable RL algorithms. We show that the computational model combining model-based and model-free control, which we term the prefrontal RL, reliably encodes the information of high-level policy that humans learned, and this model can generalize the learned policy to a wide range of tasks. First, we trained the prefrontal RL, and deep RL algorithms on 82 subjects' data, collected while human participants were performing two-stage Markov decision tasks, in which we manipulated the goal, state-transition uncertainty and state-space complexity. In the reliability test, which includes the latent behavior profile and the parameter recoverability test, we showed that the prefrontal RL reliably learned the latent policies of the humans, while all the other models failed. Second, to test the ability to generalize what these models learned from the original task, we situated them in the context of environmental volatility. Specifically, we ran large-scale simulations with 10 Markov decision tasks, in which latent context variables change over time. Our information-theoretic analysis showed that the prefrontal RL showed the highest level of adaptability and episodic encoding efficacy. This is the first attempt to formally test the possibility that computational models mimicking the way the brain solves general problems can lead to practical solutions to key challenges in machine learning.