相关论文: Multi-Stage Episodic Control for Strategic Explora…

The combination of Monte-Carlo Tree Search (MCTS) and deep reinforcement learning is state-of-the-art in two-player perfect-information games. In this paper, we describe a search algorithm that uses a variant of MCTS which we enhanced by 1)…

Humans learn to play video games significantly faster than the state-of-the-art reinforcement learning (RL) algorithms. People seem to build simple models that are easy to learn to support planning and strategic exploration. Inspired by…

Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments. However, such methods often demand extensive training time. For instance, the state-of-the-art method TiZero takes 40 days to…

This paper introduces a method for constructing an upper bound for exploration policy using either the weighted variance of return sequences or the weighted temporal difference (TD) error. We demonstrate that the variance of the return…

Training a multi-agent reinforcement learning (MARL) model with a sparse reward is generally difficult because numerous combinations of interactions among agents induce a certain outcome (i.e., success or failure). Earlier studies have…

We propose an exploration method that incorporates look-ahead search over basic learnt skills and their dynamics, and use it for reinforcement learning (RL) of manipulation policies . Our skills are multi-goal policies learned in isolation…

Efficient exploration remains a central challenge in reinforcement learning, serving as a useful pretraining objective for data collection, particularly when an external reward function is unavailable. A principled formulation of the…

Decoding strategies play a pivotal role in text generation for modern language models, yet a puzzling gap divides theory and practice. Surprisingly, strategies that should intuitively be optimal, such as Maximum a Posteriori (MAP), often…

Efficient exploration in complex environments remains a major challenge for reinforcement learning. We propose bootstrapped DQN, a simple algorithm that explores in a computationally and statistically efficient manner through use of…

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…

In the zero-shot policy transfer (ZSPT) setting for contextual Markov decision processes (MDP), agents train on a fixed set of contexts and must generalise to new ones. Recent work has argued and demonstrated that increased exploration can…

We propose Deterministic Sequencing of Exploration and Exploitation (DSEE) algorithm with interleaving exploration and exploitation epochs for model-based RL problems that aim to simultaneously learn the system model, i.e., a Markov…

We consider the task of learning to play families of text-based computer adventure games, i.e., fully textual environments with a common theme (e.g. cooking) and goal (e.g. prepare a meal from a recipe) but with different specifics; new…

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…

Exploration is an essential component of reinforcement learning algorithms, where agents need to learn how to predict and control unknown and often stochastic environments. Reinforcement learning agents depend crucially on exploration to…

Exploration efficiency is a challenging problem in multi-agent reinforcement learning (MARL), as the policy learned by confederate MARL depends on the collaborative approach among multiple agents. Another important problem is the less…

Bugs in popular distributed protocol implementations have been the source of many downtimes in popular internet services. We describe a randomized testing approach for distributed protocol implementations based on reinforcement learning.…

Exploration in environments with sparse rewards remains a fundamental challenge in reinforcement learning (RL). Existing approaches such as curriculum learning and Go-Explore often rely on hand-crafted heuristics, while curiosity-driven…

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…

The explore{exploit dilemma is one of the central challenges in Reinforcement Learning (RL). Bayesian RL solves the dilemma by providing the agent with information in the form of a prior distribution over environments; however, full…