Learn to Interpret Atari Agents
Deep reinforcement learning (DeepRL) agents surpass human-level performance in many tasks. However, the direct mapping from states to actions makes it hard to interpret the rationale behind the decision-making of the agents. In contrast to previous a-posteriori methods for visualizing DeepRL policies, in this work, we propose to equip the DeepRL model with an innate visualization ability. Our proposed agent, named region-sensitive Rainbow (RS-Rainbow), is an end-to-end trainable network based on the original Rainbow, a powerful deep Q-network agent. It learns important regions in the input domain via an attention module. At inference time, after each forward pass, we can visualize regions that are most important to decision-making by backpropagating gradients from the attention module to the input frames. The incorporation of our proposed module not only improves model interpretability, but leads to performance improvement. Extensive experiments on games from the Atari 2600 suite demonstrate the effectiveness of RS-Rainbow.
Code (1)
Tasks
Decision MakingDeep Reinforcement LearningReinforcement LearningSimilar Papers 제목 키워드 기반
HackAtari: Atari Learning Environments for Robust and Continual Reinforcement Learning
Artificial agents' adaptability to novelty and alignment with intended behavior is crucial for their effective deployment. Reinforcement learning (RL) leverages novelty as a means of exploration, yet agents often struggl…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Explaining Deep Reinforcement Learning Agents In The Atari Domain through a Surrogate Model
One major barrier to applications of deep Reinforcement Learning (RL) both inside and outside of games is the lack of explainability. In this paper, we describe a lightweight and effective method to derive explanations f…
Atari GamesDecision MakingDeep Reinforcement Learningreinforcement-learning+1The Atari Data Scraper
Reinforcement learning has made great strides in recent years due to the success of methods using deep neural networks. However, such neural networks act as a black box, obscuring the inner workings. While reinforcement …
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Learning objects from pixels
We show how discrete objects can be learnt in an unsupervised fashion from pixels, and how to perform reinforcement learning using this object representation. More precisely, we construct a differentiable mapping from a…
Atari GamesObjectPositionreinforcement-learning+2Learning To Play Atari Games Using Dueling Q-Learning and Hebbian Plasticity
In this work, an advanced deep reinforcement learning architecture is used to train neural network agents playing atari games. Given only the raw game pixels, action space, and reward information, the system can train ag…
Atari GamesDeep Reinforcement LearningLifelong learningQ-Learning