相关论文: Actor-Accelerated Policy Dual Averaging for Reinfo…
Catastrophic forgetting has a serious impact in reinforcement learning, as the data distribution is generally sparse and non-stationary over time. The purpose of this study is to investigate whether pseudorehearsal can increase performance…
Policy gradient methods hold great potential for solving complex continuous control tasks. Still, their training efficiency can be improved by exploiting structure within the optimization problem. Recent work indicates that supervised…
We propose a novel framework for efficient parallelization of deep reinforcement learning algorithms, enabling these algorithms to learn from multiple actors on a single machine. The framework is algorithm agnostic and can be applied to…
The distributed convex optimization problem over the multi-agent system is considered in this paper, and it is assumed that each agent possesses its own cost function and communicates with its neighbours over a sequence of time-varying…
We consider the problem of learning control policies that optimize a reward function while satisfying constraints due to considerations of safety, fairness, or other costs. We propose a new algorithm, Projection-Based Constrained Policy…
Most of reinforcement learning algorithms optimize the discounted criterion which is beneficial to accelerate the convergence and reduce the variance of estimates. Although the discounted criterion is appropriate for certain tasks such as…
Deterministic policy gradient algorithms are foundational for actor-critic methods in controlling continuous systems, yet they often encounter inaccuracies due to their dependence on the derivative of the critic's value estimates with…
In value-based deep reinforcement learning methods, approximation of value functions induces overestimation bias and leads to suboptimal policies. We show that in deep actor-critic methods that aim to overcome the overestimation bias, if…
To obtain better value estimation in reinforcement learning, we propose a novel algorithm based on the double actor-critic framework with temporal difference error-driven regularization, abbreviated as TDDR. TDDR employs double actors, with…
This paper augments the reward received by a reinforcement learning agent with potential functions in order to help the agent learn (possibly stochastic) optimal policies. We show that a potential-based reward shaping scheme is able to…
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…
Policy gradient methods are an appealing approach in reinforcement learning because they directly optimize the cumulative reward and can straightforwardly be used with nonlinear function approximators such as neural networks. The two main…
Learning Automata (LA) are considered as one of the most powerful tools in the field of reinforcement learning. The family of estimator algorithms is proposed to improve the convergence rate of LA and has made great achievements. However,…
A dialogue policy module is an essential part of task-completion dialogue systems. Recently, increasing interest has focused on reinforcement learning (RL)-based dialogue policy. Its favorable performance and wise action decisions rely on…
In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily…
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 consider off-policy policy evaluation with function approximation (FA) in average-reward MDPs, where the goal is to estimate both the reward rate and the differential value function. For this problem, bootstrapping is necessary and,…
Multi-agent proximal policy optimization (MAPPO) has recently demonstrated state-of-the-art performance on challenging multi-agent reinforcement learning tasks. However, MAPPO still struggles with the credit assignment problem, wherein the…
First-order stochastic optimization methods are currently the most widely used class of methods for training deep neural networks. However, the choice of the optimizer has become an ad-hoc rule that can significantly affect the performance.…
Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong…