Related papers: Variational Dynamic for Self-Supervised Exploratio…
We study the problem of learning exploration-exploitation strategies that effectively adapt to dynamic environments, where the task may change over time. While RNN-based policies could in principle represent such strategies, in practice…
The reinforcement learning paradigm allows, in principle, for complex behaviours to be learned directly from simple reward signals. In practice, however, it is common to carefully hand-design the reward function to encourage a particular…
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…
Deep reinforcement learning (DRL) has been proven its efficiency in capturing users' dynamic interests in recent literature. However, training a DRL agent is challenging, because of the sparse environment in recommender systems (RS), DRL…
We consider the problem of reinforcement learning under safety requirements, in which an agent is trained to complete a given task, typically formalized as the maximization of a reward signal over time, while concurrently avoiding…
In this work we consider partially observable environments with sparse rewards. We present a self-supervised representation learning method for image-based observations, which arranges embeddings respecting temporal distance of…
Robotic manipulation stands as a largely unsolved problem despite significant advances in robotics and machine learning in recent years. One of the key challenges in manipulation is the exploration of the dynamics of the environment when…
Modern reinforcement learning (RL) struggles to capture real-world cause-and-effect dynamics, leading to inefficient exploration due to extensive trial-and-error actions. While recent efforts to improve agent exploration have leveraged…
We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy…
In the realm of multi-agent reinforcement learning, intrinsic motivations have emerged as a pivotal tool for exploration. While the computation of many intrinsic rewards relies on estimating variational posteriors using neural network…
Sparsity of rewards while applying a deep reinforcement learning method negatively affects its sample-efficiency. A viable solution to deal with the sparsity of rewards is to learn via intrinsic motivation which advocates for adding an…
Recent advancements in deep reinforcement learning (RL) have demonstrated notable progress in sample efficiency, spanning both model-based and model-free paradigms. Despite the identification and mitigation of specific bottlenecks in prior…
Exploration is essential in reinforcement learning as an agent relies on trial and error to learn an optimal policy. However, when rewards are sparse, naive exploration strategies, like noise injection, are often insufficient. Intrinsic…
With reinforcement learning, an agent could learn complex behaviors from high-level abstractions of the task. However, exploration and reward shaping remained challenging for existing methods, especially in scenarios where the extrinsic…
Autonomous 3D environment exploration is a fundamental task for various applications such as navigation. The goal of exploration is to investigate a new environment and build its occupancy map efficiently. In this paper, we propose a new…
Positive affect has been linked to increased interest, curiosity and satisfaction in human learning. In reinforcement learning, extrinsic rewards are often sparse and difficult to define, intrinsically motivated learning can help address…
Rewards play an essential role in reinforcement learning. In contrast to rule-based game environments with well-defined reward functions, complex real-world robotic applications, such as contact-rich manipulation, lack explicit and…
Reinforcement learning can solve decision-making problems and train an agent to behave in an environment according to a predesigned reward function. However, such an approach becomes very problematic if the reward is too sparse and so the…
Learning a reward function from demonstrations suffers from low sample-efficiency. Even with abundant data, current inverse reinforcement learning methods that focus on learning from a single environment can fail to handle slight changes in…
Exploration is essential in reinforcement learning, particularly in environments where external rewards are sparse. Here we focus on exploration with intrinsic rewards, where the agent transiently augments the external rewards with…