Related papers: Self-Supervised Exploration via Disagreement

In this paper we address the challenge of exploration in deep reinforcement learning for robotic manipulation tasks. In sparse goal settings, an agent does not receive any positive feedback until randomly achieving the goal, which becomes…

We propose an approach to learning agents for active robotic mapping, where the goal is to map the environment as quickly as possible. The agent learns to map efficiently in simulated environments by receiving rewards corresponding to how…

Adaptive exploration methods propose ways to learn complex policies via alternating between exploration and exploitation. An important question for such methods is to determine the appropriate moment to switch between exploration and…

Current reinforcement learning (RL) in robotics often experiences difficulty in generalizing to new downstream tasks due to the innate task-specific training paradigm. To alleviate it, unsupervised RL, a framework that pre-trains the agent…

Exploration remains a key challenge in deep reinforcement learning (RL). Optimism in the face of uncertainty is a well-known heuristic with theoretical guarantees in the tabular setting, but how best to translate the principle to deep…

Recent works have proven that intricate cooperative behaviors can emerge in agents trained using meta reinforcement learning on open ended task distributions using self-play. While the results are impressive, we argue that self-play and…

The use of mobile robots is being popular over the world mainly for autonomous explorations in hazardous/ toxic or unknown environments. This exploration will be more effective and efficient if the explorations in unknown environment can be…

Curiosity-based reward schemes can present powerful exploration mechanisms which facilitate the discovery of solutions for complex, sparse or long-horizon tasks. However, as the agent learns to reach previously unexplored spaces and the…

Autonomous robots operating in unstructured, safety-critical environments, from planetary exploration to warehouses and homes, must learn to safely navigate and interact with their surroundings despite limited prior knowledge. Current…

In this paper, we consider the problem of building learning agents that can efficiently learn to navigate in constrained environments. The main goal is to design agents that can efficiently learn to understand and generalize to different…

Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models in RL has been made by learning models via supervised learning. But traditional model-based…

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies,…

Research in developmental psychology consistently shows that children explore the world thoroughly and efficiently and that this exploration allows them to learn. In turn, this early learning supports more robust generalization and…

Model-based Reinforcement Learning (MBRL) has emerged as a promising paradigm for autonomous driving, where data efficiency and robustness are critical. Yet, existing solutions often rely on carefully crafted, task specific extrinsic…

Robots operating alongside humans often encounter unfamiliar environments that make autonomous task completion challenging. Though improving models and increasing dataset size can enhance a robot's performance in unseen environments, data…

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…

The imbalance of exploration and exploitation has long been a significant challenge in reinforcement learning. In policy optimization, excessive reliance on exploration reduces learning efficiency, while over-dependence on exploitation…

Exploration efficiency is a challenging problem in multi-agent reinforcement learning (MARL), as the policy learned by confederate MARL depends on the collaborative approach among multiple agents. Another important problem is the less…

Autonomous navigation in crowded environments is an open problem with many applications, essential for the coexistence of robots and humans in the smart cities of the future. In recent years, deep reinforcement learning approaches have…

Reinforcement learning in sparse-reward navigation environments with expensive and limited interactions is challenging and poses a need for effective exploration. Motivated by complex navigation tasks that require real-world training (when…