Related papers: Is prioritized sweeping the better episodic contro…

Episodic memory-based methods can rapidly latch onto past successful strategies by a non-parametric memory and improve sample efficiency of traditional reinforcement learning. However, little effort is put into the continuous domain, where…

The sample-inefficiency problem in Artificial Intelligence refers to the inability of current Deep Reinforcement Learning models to optimize action policies within a small number of episodes. Recent studies have tried to overcome this…

Experience replay, the reuse of past data to improve sample efficiency, is ubiquitous in reinforcement learning. Though a variety of smart sampling schemes have been introduced to improve performance, uniform sampling by far remains the…

We investigate the robustness properties of image recognition models equipped with two features inspired by human vision, an explicit episodic memory and a shape bias, at the ImageNet scale. As reported in previous work, we show that an…

Episodic memory plays an important role in the behavior of animals and humans. It allows the accumulation of information about current state of the environment in a task-agnostic way. This episodic representation can be later accessed by…

We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in this setting is to design algorithms that select informative…

During sleep and awake rest, the hippocampus replays sequences of place cells that have been activated during prior experiences. These have been interpreted as a memory consolidation process, but recent results suggest a possible…

The goal of this paper is to analyze distributional Markov Decision Processes as a class of control problems in which the objective is to learn policies that steer the distribution of a cumulative reward toward a prescribed target law,…

Prioritized experience replay is a reinforcement learning technique whereby agents speed up learning by replaying useful past experiences. This usefulness is quantified as the expected gain from replaying the experience, a quantity often…

Episodic memory -- the ability to recall specific events grounded in time and space -- is a cornerstone of human cognition, enabling not only coherent storytelling, but also planning and decision-making. Despite their remarkable…

Deep Deterministic Policy Gradient (DDPG) has been proved to be a successful reinforcement learning (RL) algorithm for continuous control tasks. However, DDPG still suffers from data insufficiency and training inefficiency, especially in…

Prompt optimization is essential for enhancing the performance of Large Language Models (LLMs) in a range of Natural Language Processing (NLP) tasks, particularly in scenarios of few-shot learning where training examples are incorporated…

Many tasks require flexibly modifying perception and behavior based on current goals. Humans can retrieve episodic memories from days to years ago, using them to contextualize and generalize behaviors across novel but structurally related…

Episodic self-imitation learning, a novel self-imitation algorithm with a trajectory selection module and an adaptive loss function, is proposed to speed up reinforcement learning. Compared to the original self-imitation learning algorithm,…

Episodic memory plays a crucial role in various cognitive processes, such as the ability to mentally recall past events. While cognitive science emphasizes the significance of spatial context in the formation and retrieval of episodic…

To make good decisions in the real world people need efficient planning strategies because their computational resources are limited. Knowing which planning strategies would work best for people in different situations would be very useful…

Both the human brain and artificial learning agents operating in real-world or comparably complex environments are faced with the challenge of online model selection. In principle this challenge can be overcome: hierarchical Bayesian…

Most reinforcement learning algorithms take advantage of an experience replay buffer to repeatedly train on samples the agent has observed in the past. Not all samples carry the same amount of significance and simply assigning equal…

Markovian processes have long been used to model stochastic environments. Reinforcement learning has emerged as a framework to solve sequential planning and decision-making problems in such environments. In recent years, attempts were made…

When optimizing problems with uncertain parameter values in a linear objective, decision-focused learning enables end-to-end learning of these values. We are interested in a stochastic scheduling problem, in which processing times are…