相关论文: Empowerment-driven Exploration using Mutual Inform…

Exploration of mechanisms underlying the emergence of collective cooperation remains a focal point in field of evolution of cooperation. Prevailing studies often neglect historical information, relying on the latest rewards as the primary…

This paper presents an algorithmic framework for learning robust policies in asymmetric imperfect-information games, where the joint reward could depend on the uncertain opponent type (a private information known only to the opponent itself…

Reinforcement learning for the optimization of quantum circuits uses an agent whose goal is to maximize the value of a reward function that decides what is correct and what is wrong during the exploration of the search space. It is an open…

Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to…

Maximum entropy reinforcement learning motivates agents to explore states and actions to maximize the entropy of some distribution, typically by providing additional intrinsic rewards proportional to that entropy function. In this paper, we…

Reinforcement learning with sparse rewards is challenging because an agent can rarely obtain non-zero rewards and hence, gradient-based optimization of parameterized policies can be incremental and slow. Recent work demonstrated that using…

Learning complex robot behavior through interactions with the environment necessitates principled exploration. Effective strategies should prioritize exploring regions of the state-action space that maximize rewards, with optimistic…

Unsupervised exploration and representation learning become increasingly important when learning in diverse and sparse environments. The information-theoretic principle of empowerment formalizes an unsupervised exploration objective through…

Equipping artificial agents with useful exploration mechanisms remains a challenge to this day. Humans, on the other hand, seem to manage the trade-off between exploration and exploitation effortlessly. In the present article, we put…

We study the use of randomized value functions to guide deep exploration in reinforcement learning. This offers an elegant means for synthesizing statistically and computationally efficient exploration with common practical approaches to…

We consider the multi-agent reinforcement learning setting with imperfect information in which each agent is trying to maximize its own utility. The reward function depends on the hidden state (or goal) of both agents, so the agents must…

Existing approaches for improving generalization in deep reinforcement learning (RL) have mostly focused on representation learning, neglecting RL-specific aspects such as exploration. We hypothesize that the agent's exploration strategy…

Incomplete knowledge of the environment leads an agent to make decisions under uncertainty. One of the major dilemmas in Reinforcement Learning (RL) where an autonomous agent has to balance two contrasting needs in making its decisions is:…

Multi-agent reinforcement learning involves multiple agents interacting with each other and a shared environment to complete tasks. When rewards provided by the environment are sparse, agents may not receive immediate feedback on the…

Mutual relationships, such as cooperation and exploitation, are the basis of human and other biological societies. The foundations of these relationships are rooted in the decision making of individuals, and whether they choose to be…

We introduce an exploration bonus for deep reinforcement learning methods calculated using self-organising feature maps. Our method uses adaptive resonance theory (ART) providing online, unsupervised clustering to quantify the novelty of a…

We propose a reinforcement learning agent to solve hard exploration games by learning a range of directed exploratory policies. We construct an episodic memory-based intrinsic reward using k-nearest neighbors over the agent's recent…

Reinforcement learning (RL) studies how an agent comes to achieve reward in an environment through interactions over time. Recent advances in machine RL have surpassed human expertise at the world's oldest board games and many classic video…

Multiagent reinforcement learning, as a prominent intelligent paradigm, enables collaborative decision-making within complex systems. However, existing approaches often rely on explicit action exchange between agents to evaluate action…

We propose a new method for count-based exploration in high-dimensional state spaces. Unlike previous work which relies on density models, we show that counts can be derived by averaging samples from the Rademacher distribution (or coin…