paper-with-me

Papers

Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning

2023-02-07 · Lukas Schäfer, Oliver Slumbers, Stephen Mcaleer, Yali Du, Stefano V. Albrecht, David Mguni

Multi-agent reinforcement learning (MARL) requires agents to explore within a vast joint action space to find joint actions that lead to coordination. Existing value-based MARL algorithms commonly rely on random exploration, such as $\epsilon$-greedy, to explore the environment which is not systematic and inefficient at identifying effective actions in multi-agent problems. Additionally, the concurrent training of the policies of multiple agents during training can render the optimisation non-stationary. This can lead to unstable value estimates, highly variant gradients, and ultimately hinder coordination between agents. To address these challenges, we propose ensemble value functions for multi-agent exploration (EMAX). EMAX is a framework to seamlessly extend value-based MARL algorithms. EMAX leverages an ensemble of value functions for each agent to guide their exploration, reduce the variance of their optimisation, and makes their policies more robust to miscoordination. EMAX achieves these benefits by (1) systematically guiding the exploration of agents with a UCB policy towards parts of the environment that require multiple agents to coordinate. (2) EMAX computes average value estimates across the ensemble as target values to reduce the variance of gradients and make optimisation more stable. (3) During evaluation, EMAX selects actions following a majority vote across the ensemble to reduce the likelihood of miscoordination. We first instantiate independent DQN with EMAX and evaluate it in 11 general-sum tasks with sparse rewards. We show that EMAX improves final evaluation returns by 185% across all tasks. We then evaluate EMAX on top of IDQN, VDN and QMIX in 21 common-reward tasks, and show that EMAX improves sample efficiency and final evaluation returns across all tasks over all three vanilla algorithms by 60%, 47%, and 538%, respectively.

📄 PDF Abstract BibTeX arXiv:2302.03439

Code (0)

등록된 구현이 없습니다.

Tasks

Efficient ExplorationMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…
DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…

Similar Papers 제목 키워드 기반

Value Bonuses using Ensemble Errors for Exploration in Reinforcement Learning

2026-02-12 · Abdul Wahab, Raksha Kumaraswamy, Martha White arxiv

Optimistic value estimates provide one mechanism for directed exploration in reinforcement learning (RL). The agent acts greedily with respect to an estimate of the value plus what can be seen as a value bonus. The value…

Reinforcement Learning

Uncertainty - sensitive learning and planning with ensembles

2019-09-25 · Piotr Miłoś, Łukasz Kuciński, Konrad Czechowski, Piotr Kozakowski 외

We propose a reinforcement learning framework for discrete environments in which an agent optimizes its behavior on two timescales. For the short one, it uses tree search methods to perform tactical decisions. The long s…

Montezuma's RevengeSokoban

Model-Value Inconsistency as a Signal for Epistemic Uncertainty

2021-12-08 · Angelos Filos, Eszter Vértes, Zita Marinho, Gregory Farquhar 외

Using a model of the environment and a value function, an agent can construct many estimates of a state's value, by unrolling the model for different lengths and bootstrapping with its value function. Our key insight is …

Model-based Reinforcement LearningRolling Shutter Correction

Diverse Priors for Deep Reinforcement Learning

2023-10-23 · Chenfan Weng, Zhongguo Li

In Reinforcement Learning (RL), agents aim at maximizing cumulative rewards in a given environment. During the learning process, RL agents face the dilemma of exploitation and exploration: leveraging existing knowledge t…

Deep Reinforcement LearningDiversityreinforcement-learningReinforcement Learning+1

Centralized Cooperative Exploration Policy for Continuous Control Tasks

2023-01-06 · Chao Li, Chen Gong, Qiang He, Xinwen Hou 외

The deep reinforcement learning (DRL) algorithm works brilliantly on solving various complex control tasks. This phenomenal success can be partly attributed to DRL encouraging intelligent agents to sufficiently explore t…

continuous-controlContinuous ControlDeep Reinforcement Learning