相关论文: Explore to Generalize in Zero-Shot RL

A highly desirable property of a reinforcement learning (RL) agent -- and a major difficulty for deep RL approaches -- is the ability to generalize policies learned on a few tasks over a high-dimensional observation space to similar tasks…

Reinforcement learning has the potential to automate the acquisition of behavior in complex settings, but in order for it to be successfully deployed, a number of practical challenges must be addressed. First, in real world settings, when…

Many important real-world problems have action spaces that are high-dimensional, continuous or both, making full enumeration of all possible actions infeasible. Instead, only small subsets of actions can be sampled for the purpose of policy…

In robot manipulation, Reinforcement Learning (RL) often suffers from low sample efficiency and uncertain convergence, especially in large observation and action spaces. Foundation Models (FMs) offer an alternative, demonstrating promise in…

Zero-shot inference is a powerful paradigm that enables the use of large pretrained models for downstream classification tasks without further training. However, these models are vulnerable to inherited biases that can impact their…

Recent advances in large language models (LLMs) have demonstrated remarkable capabilities in reasoning and tool utilization. However, the generalization of tool-augmented reinforcement learning (RL) across diverse domains remains a…

In the zero-shot policy transfer setting in reinforcement learning, the goal is to train an agent on a fixed set of training environments so that it can generalise to similar, but unseen, testing environments. Previous work has shown that…

In this paper, we consider the problem of building learning agents that can efficiently learn to navigate in constrained environments. The main goal is to design agents that can efficiently learn to understand and generalize to different…

Recent advances in vision-based navigation and exploration have shown impressive capabilities in photorealistic indoor environments. However, these methods still struggle with long-horizon tasks and require large amounts of data to…

In this study, we address the problem of efficient exploration in reinforcement learning. Most common exploration approaches depend on random action selection, however these approaches do not work well in environments with sparse or no…

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…

Exploration is fundamental to reinforcement learning (RL), as it determines how effectively an agent discovers and exploits the underlying structure of its environment to achieve optimal performance. Existing exploration methods generally…

While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement…

This paper presents a novel form of policy gradient for model-free reinforcement learning (RL) with improved exploration properties. Current policy-based methods use entropy regularization to encourage undirected exploration of the reward…

The ability to generalize to previously unseen tasks with little to no supervision is a key challenge in modern machine learning research. It is also a cornerstone of a future "General AI". Any artificially intelligent agent deployed in a…

Agents trained with deep reinforcement learning algorithms are capable of performing highly complex tasks including locomotion in continuous environments. We investigate transferring the learning acquired in one task to a set of previously…

In reinforcement learning, abstraction methods that remove unnecessary information from the observation are commonly used to learn policies which generalize better to unseen tasks. However, these methods often overlook a crucial weakness:…

Recent work has shown that, under certain assumptions, zero-shot reinforcement learning (RL) methods can generalise to any unseen task in an environment after reward-free pre-training. Access to Markov states is one such assumption, yet, in…

Supervised learning (SL) and reinforcement learning (RL) are both widely used to train general-purpose agents for complex tasks, yet their generalization capabilities and underlying mechanisms are not yet fully understood. In this paper, we…

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…