Related papers: Characterizing the Gap Between Actor-Critic and Po…
Exploration-exploitation dilemma has long been a crucial issue in reinforcement learning. In this paper, we propose a new approach to automatically balance between these two. Our method is built upon the Soft Actor-Critic (SAC) algorithm,…
Cooperative problems under continuous control have always been the focus of multi-agent reinforcement learning. Existing algorithms suffer from the problem of uneven learning degree with the increase of the number of agents. In this paper,…
Model Predictive Control has been recently proposed as policy approximation for Reinforcement Learning, offering a path towards safe and explainable Reinforcement Learning. This approach has been investigated for Q-learning and actor-critic…
Robust Reinforcement Learning aims to derive optimal behavior that accounts for model uncertainty in dynamical systems. However, previous studies have shown that by considering the worst case scenario, robust policies can be overly…
Safety is essential for reinforcement learning (RL) applied in real-world situations. Chance constraints are suitable to represent the safety requirements in stochastic systems. Previous chance-constrained RL methods usually have a low…
This paper introduces the Active-Importance-Sampling Actor-Critic (AISAC) algorithm, an extension of the Actor-Critic framework for reducing variance in policy gradient estimation. AISAC optimizes the behavior policy to minimize gradient…
Most approaches to visual scene analysis have emphasised parallel processing of the image elements. However, one area in which the sequential nature of vision is apparent, is that of segmenting multiple, potentially similar and partially…
Model-free deep reinforcement learning has achieved great success in many domains, such as video games, recommendation systems and robotic control tasks. In continuous control tasks, widely used policies with Gaussian distributions results…
Multi-agent reinforcement learning in mixed-motive settings presents a fundamental challenge: agents must balance individual interests with collective goals, which are neither fully aligned nor strictly opposed. To address this, reward…
Centralized Training for Decentralized Execution, where training is done in a centralized offline fashion, has become a popular solution paradigm in Multi-Agent Reinforcement Learning. Many such methods take the form of actor-critic with…
Deep reinforcement learning, and especially the Asynchronous Advantage Actor-Critic algorithm, has been successfully used to achieve super-human performance in a variety of video games. Starcraft II is a new challenge for the reinforcement…
Soft Actor-Critic (SAC) is an off-policy actor-critic reinforcement learning algorithm, essentially based on entropy regularization. SAC trains a policy by maximizing the trade-off between expected return and entropy (randomness in the…
Compared to on-policy counterparts, off-policy model-free deep reinforcement learning can improve data efficiency by repeatedly using the previously gathered data. However, off-policy learning becomes challenging when the discrepancy…
We propose MADDPG-K, a scalable extension to Multi-Agent Deep Deterministic Policy Gradient (MADDPG) that addresses the computational limitations of centralized critic approaches. Centralized critics, which condition on the observations and…
Policy Dual Averaging (PDA) offers a principled Policy Mirror Descent (PMD) framework that more naturally admits value function approximation than standard PMD, enabling the use of approximate advantage (or Q-) functions while retaining…
We propose a new variant of the strategic classification problem: a principal reveals a classifier, and $n$ agents report their (possibly manipulated) features to be classified. Motivated by real-world applications, our model crucially…
Cooperative multi-agent systems can be naturally used to model many real world problems, such as network packet routing and the coordination of autonomous vehicles. There is a great need for new reinforcement learning methods that can…
Policy gradient methods have become popular in multi-agent reinforcement learning, but they suffer from high variance due to the presence of environmental stochasticity and exploring agents (i.e., non-stationarity), which is potentially…
In this paper, we introduce a generalization of the standard Stackelberg Games (SGs) framework: Calibrated Stackelberg Games (CSGs). In CSGs, a principal repeatedly interacts with an agent who (contrary to standard SGs) does not have direct…
A key open challenge in agile quadrotor flight is how to combine the flexibility and task-level generality of model-free reinforcement learning (RL) with the structure and online replanning capabilities of model predictive control (MPC),…