相关论文: Learning telic-controllable state representations

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…

Self-supervised goal proposal and reaching is a key component for exploration and efficient policy learning algorithms. Such a self-supervised approach without access to any oracle goal sampling distribution requires deep exploration and…

Environments with controllable dynamics are usually understood in terms of explicit models. However, such models are not always available, but may sometimes be learned by exploring an environment. In this work, we investigate using an…

For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires. Furthermore, to provide the requisite level of generality, these skills…

Recent years have seen an increasing amount of work on embodied AI agents that can perform tasks by following human language instructions. However, most of these agents are reactive, meaning that they simply learn and imitate behaviors…

A key challenge in scaling up Reinforcement Learning is generalizing learned behaviour. Without the ability to carry forward acquired knowledge an agent is doomed to learn each task from scratch. In this paper we develop a new formalism for…

Understanding a \textit{reinforcement learning} policy, which guides state-to-action mappings to maximize rewards, necessitates an accompanying explanation for human comprehension. In this paper, we introduce a set of \textit{linear…

This paper presents an approach that brings together game theory with grammatical inference and discrete abstractions in order to synthesize control strategies for hybrid dynamical systems performing tasks in partially unknown but…

We present a representation-driven framework for reinforcement learning. By representing policies as estimates of their expected values, we leverage techniques from contextual bandits to guide exploration and exploitation. Particularly,…

Interventions are central to causal learning and reasoning. Yet ultimately an intervention is an abstraction: an agent embedded in a physical environment (perhaps modeled as a Markov decision process) does not typically come equipped with…

In this paper, we study a transfer reinforcement learning problem where the state transitions and rewards are affected by the environmental context. Specifically, we consider a demonstrator agent that has access to a context-aware policy…

Developing agents that can execute multiple skills by learning from pre-collected datasets is an important problem in robotics, where online interaction with the environment is extremely time-consuming. Moreover, manually designing reward…

When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task -- the task ``features" -- as well as how to combine these features…

We study the problem of learning goal-conditioned policies in Minecraft, a popular, widely accessible yet challenging open-ended environment for developing human-level multi-task agents. We first identify two main challenges of learning…

Neuro-symbolic reinforcement learning (NS-RL) has emerged as a promising paradigm for explainable decision-making, characterized by the interpretability of symbolic policies. NS-RL entails structured state representations for tasks with…

Problems which require both long-horizon planning and continuous control capabilities pose significant challenges to existing reinforcement learning agents. In this paper we introduce a novel hierarchical reinforcement learning agent which…

Controllability has become a crucial aspect of trustworthy machine learning, enabling learners to meet predefined targets and adapt dynamically at test time without requiring retraining as the targets shift. We provide a formal definition…

Learning from demonstration is an effective method for human users to instruct desired robot behaviour. However, for most non-trivial tasks of practical interest, efficient learning from demonstration depends crucially on inductive bias in…

In computational reinforcement learning, a growing body of work seeks to express an agent's model of the world through predictions about future sensations. In this manuscript we focus on predictions expressed as General Value Functions:…

In the absence of external rewards, agents can still learn useful behaviors by identifying and mastering a set of diverse skills within their environment. Existing skill learning methods use mutual information objectives to incentivize each…