相关论文: Pretraining Deep Actor-Critic Reinforcement Learni…

Reinforcement learning (RL) has become a promising paradigm for optimizing Retrieval-Augmented Generation (RAG) in complex reasoning tasks. However, traditional outcome-based RL approaches often suffer from reward sparsity and inefficient…

Continuous control Deep Reinforcement Learning (RL) approaches are known to suffer from estimation biases, leading to suboptimal policies. This paper introduces innovative methods in RL, focusing on addressing and exploiting estimation…

The theory of continuous-time reinforcement learning (RL) has progressed rapidly in recent years. While the ultimate objective of RL is typically to learn deterministic control policies, most existing continuous-time RL methods rely on…

Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of…

Predictive power allocation is conceived for energy-efficient video streaming over mobile networks using deep reinforcement learning. The goal is to minimize the accumulated energy consumption of each base station over a complete video…

The past few years have seen rapid progress in combining reinforcement learning (RL) with deep learning. Various breakthroughs ranging from games to robotics have spurred the interest in designing sophisticated RL algorithms and systems.…

Deep reinforcement learning has been shown to be a powerful framework for learning policies from complex high-dimensional sensory inputs to actions in complex tasks, such as the Atari domain. In this paper, we explore output representation…

Neural Network based approximations of the Value function make up the core of leading Policy Based methods such as Trust Regional Policy Optimization (TRPO) and Proximal Policy Optimization (PPO). While this adds significant value when…

Deep neural networks provide Reinforcement Learning (RL) powerful function approximators to address large-scale decision-making problems. However, these approximators introduce challenges due to the non-stationary nature of RL training. One…

In robotics, it is often not possible to learn useful policies using pure model-free reinforcement learning without significant reward shaping or curriculum learning. As a consequence, many researchers rely on expert demonstrations to guide…

We propose Automatic Curricula via Expert Demonstrations (ACED), a reinforcement learning (RL) approach that combines the ideas of imitation learning and curriculum learning in order to solve challenging robotic manipulation tasks with…

This paper presents the first actor-critic algorithm for off-policy reinforcement learning. Our algorithm is online and incremental, and its per-time-step complexity scales linearly with the number of learned weights. Previous work on…

We propose a metalearning approach for learning gradient-based reinforcement learning (RL) algorithms. The idea is to evolve a differentiable loss function, such that an agent, which optimizes its policy to minimize this loss, will achieve…

Deep learning and reinforcement learning methods have recently been used to solve a variety of problems in continuous control domains. An obvious application of these techniques is dexterous manipulation tasks in robotics which are…

Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve this. However,…

Reinforcement learning (RL) is a powerful machine learning technique that enables an intelligent agent to learn an optimal policy that maximizes the cumulative rewards in sequential decision making. Most of methods in the existing…

Applying deep reinforcement learning (RL) on real systems suffers from slow data sampling. We propose an enhanced generative adversarial network (EGAN) to initialize an RL agent in order to achieve faster learning. The EGAN utilizes the…

As the demand for autonomous driving increases, it is paramount to ensure safety. Early accident prediction using deep learning methods for driving safety has recently gained much attention. In this task, early accident prediction and a…

In this work we describe a novel deep reinforcement learning architecture that allows multiple actions to be selected at every time-step in an efficient manner. Multi-action policies allow complex behaviours to be learnt that would…

Methods to learn under algorithmic triage have predominantly focused on supervised learning settings where each decision, or prediction, is independent of each other. Under algorithmic triage, a supervised learning model predicts a fraction…