Related papers: Exploration and Incentives in Reinforcement Learni…
How to incentivize self-interested agents to explore when they prefer to exploit? Consider a population of self-interested agents that make decisions under uncertainty. They "explore" to acquire new information and "exploit" this…
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…
While learning in an unknown Markov Decision Process (MDP), an agent should trade off exploration to discover new information about the MDP, and exploitation of the current knowledge to maximize the reward. Although the agent will…
Exploration algorithms for reinforcement learning typically replace or augment the reward function with an additional ``intrinsic'' reward that trains the agent to seek previously unseen states of the environment. Here, we consider an…
A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world,…
In this paper we consider the problem of how a reinforcement learning agent that is tasked with solving a sequence of reinforcement learning problems (a sequence of Markov decision processes) can use knowledge acquired early in its lifetime…
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…
The Exploration-Exploitation tradeoff arises in Reinforcement Learning when one cannot tell if a policy is optimal. Then, there is a constant need to explore new actions instead of exploiting past experience. In practice, it is common to…
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…
Exploration is one of the most important tasks in Reinforcement Learning, but it is not well-defined beyond finite problems in the Dynamic Programming paradigm (see Subsection 2.4). We provide a reinterpretation of exploration which can be…
Exploration is an essential part of reinforcement learning, which restricts the quality of learned policy. Hard-exploration environments are defined by huge state space and sparse rewards. In such conditions, an exhaustive exploration of…
Exploration is essential for reinforcement learning (RL). To face the challenges of exploration, we consider a reward-free RL framework that completely separates exploration from exploitation and brings new challenges for exploration…
Several recent works have been dedicated to unsupervised reinforcement learning in a single environment, in which a policy is first pre-trained with unsupervised interactions, and then fine-tuned towards the optimal policy for several…
We introduce exploration potential, a quantity that measures how much a reinforcement learning agent has explored its environment class. In contrast to information gain, exploration potential takes the problem's reward structure into…
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…
Exploration in complex domains is a key challenge in reinforcement learning, especially for tasks with very sparse rewards. Recent successes in deep reinforcement learning have been achieved mostly using simple heuristic exploration…
Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP. Many of the existing exploration frameworks such as $E^3$, $R_{max}$, Thompson sampling assume a single stationary MDP and are not…
We consider a class of reinforcement-learning systems in which the agent follows a behavior policy to explore a discrete state-action space to find an optimal policy while adhering to some restriction on its behavior. Such restriction may…
A central challenge in reinforcement learning is discovering effective policies for tasks where rewards are sparsely distributed. We postulate that in the absence of useful reward signals, an effective exploration strategy should seek out…
Reinforcement Learning has emerged as a strong alternative to solve optimization tasks efficiently. The use of these algorithms highly depends on the feedback signals provided by the environment in charge of informing about how good (or…