Related papers: Curiosity-driven Exploration by Self-supervised Pr…

Infants often exhibit goal-directed behaviors, such as reaching for a sensory stimulus, even when no external reward criterion is provided. These intrinsically motivated behaviors facilitate spontaneous exploration and learning of the body…

Learning requires both study and curiosity. A good learner is not only good at extracting information from the data given to it, but also skilled at finding the right new information to learn from. This is especially true when a human…

Learning to solve tasks from a sparse reward signal is a major challenge for standard reinforcement learning (RL) algorithms. However, in the real world, agents rarely need to solve sparse reward tasks entirely from scratch. More often, we…

Training robust reasoning vision-language models (VLMs) in rare domains (such as geospatial) is fundamentally constrained by supervision scarcity. While raw geospatial imagery is abundant, the amount of task-direct supervision falls far…

Designing a distribution of environments in which RL agents can learn interesting and useful skills is a challenging and poorly understood task, for multi-agent environments the difficulties are only exacerbated. One approach is to train a…

Dynamic game theory is an increasingly popular tool for modeling multi-agent, e.g. human-robot, interactions. Game-theoretic models presume that each agent wishes to minimize a private cost function that depends on others' actions. These…

Efficient exploration is a long-standing problem in reinforcement learning since extrinsic rewards are usually sparse or missing. A popular solution to this issue is to feed an agent with novelty signals as intrinsic rewards. In this work,…

Reward design for reinforcement learning agents can be difficult in situations where one not only wants the agent to achieve some effect in the world but where one also cares about how that effect is achieved. For example, we might wish for…

Successfully navigating a complex environment to obtain a desired outcome is a difficult task, that up to recently was believed to be capable only by humans. This perception has been broken down over time, especially with the introduction…

Autonomous robots frequently need to detect "interesting" scenes to decide on further exploration, or to decide which data to share for cooperation. These scenarios often require fast deployment with little or no training data. Prior work…

Both entropy-minimizing and entropy-maximizing (curiosity) objectives for unsupervised reinforcement learning (RL) have been shown to be effective in different environments, depending on the environment's level of natural entropy. However,…

One of the bottlenecks preventing Deep Reinforcement Learning algorithms (DRL) from real-world applications is how to explore the environment and collect informative transitions efficiently. The present paper describes bounded exploration,…

Reinforcement learning (RL) agents are particularly hard to train when rewards are sparse. One common solution is to use intrinsic rewards to encourage agents to explore their environment. However, recent intrinsic exploration methods often…

In continuous control, exploration is often performed through undirected strategies in which parameters of the networks or selected actions are perturbed by random noise. Although the deep setting of undirected exploration has been shown to…

Local prediction-error-based curiosity rewards focus on the current transition without considering the world model's cumulative prediction error across all visited transitions. We introduce Curiosity-Critic, which grounds its intrinsic…

Exploration is widely regarded as one of the most challenging aspects of reinforcement learning (RL), with many naive approaches succumbing to exponential sample complexity. To isolate the challenges of exploration, we propose a new…

We propose a curiosity reward based on information theory principles and consistent with the animal instinct to maintain certain critical parameters within a bounded range. Our experimental validation shows the added value of the additional…

Learning and adaptation play great role in emergent socio-economic phenomena. Complex dynamics has been previously found in the systems of multiple learning agents interacting via a simple game. Meanwhile, the single agent adaptation is…

This work presents an architecture that generates curiosity-driven goal-directed exploration behaviours for an image sensor of a microfarming robot. A combination of deep neural networks for offline unsupervised learning of low-dimensional…

Advancements in reinforcement learning have produced a variety of complex and useful intrinsic driving forces; crucially, these drivers operate under a direct conditioning paradigm. This form of conditioning limits our agents' capacity by…