Unifying Count-Based Exploration and Intrinsic Motivation | HTML5

We consider an agent’s uncertainty about its environment and the problem of generalizing this uncertainty across states. Specifically, we focus on the problem of exploration in non-tabular reinforcement learning. Drawing inspiration from the intrinsic motivation literature, we use density models to measure uncertainty, and propose a novel algorithm for deriving a pseudo-count from an arbitrary density model. This technique enables us to generalize count-based exploration algorithms to the non-tabular case. We apply our ideas to Atari 2600 games, providing sensible pseudo-counts from raw pixels. We transform these pseudo-counts into exploration bonuses and obtain significantly improved exploration in a number of hard games, including the infamously difficult Montezuma’s Revenge. Exploration algorithms for Markov Decision Processes (MDPs) are typically concerned with reducing the agent’s uncertainty over the environment’s reward and transition functions. In a tabular setting, this uncert

Unifying Count-Based Exploration and Intrinsic Motivation Marc G. Bellemare bellemare@google.com &Sriram Srinivasan srsrinivasan@google.com &Georg Ostrovski ostrovski@google.com &Tom Schaul schaul@google.com &David Saxton saxton@google.com Google DeepMind London, United Kingdom &Rémi Munos munos@google.com Abstract We consider an agent’s uncertainty about its environment and the problem of generalizing this uncertainty across states. Specifically, we focus on the problem of exploration in non-tabular reinforcement learning. Drawing inspiration from the intrinsic motivation literature, we use d

related reading

• Exploration Strategies in Deep Reinforcement Learning | Lil'Loglilianweng.github.io
• A (Long) Peek into Reinforcement Learning | Lil'Loglilianweng.github.io
• Exploration for the Efficient Deployment of Reinforcement Learning Agentsopenreview.net
• [1705.05363] Curiosity-driven Exploration by Self-supervised Predictionar5iv.labs.arxiv.org
• [2210.05805] Exploration via Elliptical Episodic Bonusesar5iv.labs.arxiv.org
• Reward is not the optimization target — LessWronglesswrong.com
• pdfopenreview.net
• The Bayes Banditfrancesco215.github.io
• The Multi-Armed Bandit Problem and Its Solutions | Lil'Loglilianweng.github.io
• Key Papers in Deep RL - Spinning Up documentationspinningup.openai.com
• [1805.12114] Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelsar5iv.labs.arxiv.org
• Reinforcement Learning via Implicit Imitation Guidancearxiv.org