Related papers: Constrained Ensemble Exploration for Unsupervised …

Unsupervised Reinforcement Learning (RL) aims to discover diverse behaviors that can accelerate the learning of downstream tasks. Previous methods typically focus on entropy-based exploration or empowerment-driven skill learning. However,…

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…

Unsupervised reinforcement learning (RL) studies how to leverage environment statistics to learn useful behaviors without the cost of reward engineering. However, a central challenge in unsupervised RL is to extract behaviors that…

How can a reinforcement learning (RL) agent prepare to solve downstream tasks if those tasks are not known a priori? One approach is unsupervised skill discovery, a class of algorithms that learn a set of policies without access to a reward…

Representation learning and unsupervised skill discovery can allow robots to acquire diverse and reusable behaviors without the need for task-specific rewards. In this work, we use unsupervised reinforcement learning to learn a latent…

Acquiring abilities in the absence of a task-oriented reward function is at the frontier of reinforcement learning research. This problem has been studied through the lens of empowerment, which draws a connection between option discovery…

Exploration strategy design is one of the challenging problems in reinforcement learning~(RL), especially when the environment contains a large state space or sparse rewards. During exploration, the agent tries to discover novel areas or…

Motivated by the prevailing paradigm of using unsupervised learning for efficient exploration in reinforcement learning (RL) problems [tang2017exploration,bellemare2016unifying], we investigate when this paradigm is provably efficient. We…

This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible. Unsupervised skill discovery seeks to acquire different useful skills…

In reinforcement learning, unsupervised skill discovery aims to learn diverse skills without extrinsic rewards. Previous methods discover skills by maximizing the mutual information (MI) between states and skills. However, such an MI…

Effective and intelligent exploration has been an unresolved problem for reinforcement learning. Most contemporary reinforcement learning relies on simple heuristic strategies such as $\epsilon$-greedy exploration or adding Gaussian noise…

We present a new model-based algorithm for reinforcement learning (RL) which consists of explicit exploration and exploitation phases, and is applicable in large or infinite state spaces. The algorithm maintains a set of dynamics models…

Reinforcement learning (RL) methods have been shown to be capable of learning intelligent behavior in rich domains. However, this has largely been done in simulated domains without adequate focus on the process of building the simulator. In…

Unsupervised skill discovery carries the promise that an intelligent agent can learn reusable skills through autonomous, reward-free environment interaction. Existing unsupervised skill discovery methods learn skills by encouraging…

Meta-reinforcement learning (meta-RL) aims to quickly solve new tasks by leveraging knowledge from prior tasks. However, previous studies often assume a single mode homogeneous task distribution, ignoring possible structured heterogeneity…

To increase autonomy in reinforcement learning, agents need to learn useful behaviours without reliance on manually designed reward functions. To that end, skill discovery methods have been used to learn the intrinsic options available to…

A promising technique for exploration is to maximize the entropy of visited state distribution, i.e., state entropy, by encouraging uniform coverage of visited state space. While it has been effective for an unsupervised setup, it tends to…

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…

Mutual information-based reinforcement learning (RL) has been proposed as a promising framework for retrieving complex skills autonomously without a task-oriented reward function through mutual information (MI) maximization or variational…

This paper proposes \emph{Episodic and Lifelong Exploration via Maximum ENTropy} (ELEMENT), a novel, multiscale, intrinsically motivated reinforcement learning (RL) framework that is able to explore environments without using any extrinsic…