Related papers: Decoupling Meta-Reinforcement Learning with Gaussi…
We propose a general formulation for addressing reinforcement learning (RL) problems in settings with observational data. That is, we consider the problem of learning good policies solely from historical data in which unobserved factors…
Trial-and-error based reinforcement learning (RL) has seen rapid advancements in recent times, especially with the advent of deep neural networks. However, the majority of autonomous RL algorithms require a large number of interactions with…
Deep Reinforcement Learning (DRL) enables robots to perform some intelligent tasks end-to-end. However, there are still many challenges for long-horizon sparse-reward robotic manipulator tasks. On the one hand, a sparse-reward setting…
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,…
Offline multi-task reinforcement learning aims to learn a unified policy capable of solving multiple tasks using only pre-collected task-mixed datasets, without requiring any online interaction with the environment. However, it faces…
This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL). MQL builds upon three simple ideas. First, we show that Q-learning is competitive with state-of-the-art meta-RL algorithms if…
A number of deep reinforcement-learning (RL) approaches propose to control traffic signals. In this work, we study the robustness of such methods along two axes. First, sensor failures and GPS occlusions create missing-data challenges and…
In order for robots to perform mission-critical tasks, it is essential that they are able to quickly adapt to changes in their environment as well as to injuries and or other bodily changes. Deep reinforcement learning has been shown to be…
Unsupervised pretraining has driven empirical advances in goal-conditioned reinforcement learning (GCRL), but its theoretical foundations remain poorly understood. In particular, an influential class of methods, mutual information skill…
The high cost of real-world data for robotics Reinforcement Learning (RL) leads to the wide usage of simulators. Despite extensive work on building better dynamics models for simulators to match with the real world, there is another,…
There is considerable interest in designing meta-reinforcement learning (meta-RL) algorithms, which enable autonomous agents to adapt new tasks from small amount of experience. In meta-RL, the specification (such as reward function) of…
Many reinforcement learning (RL) tasks have specific properties that can be leveraged to modify existing RL algorithms to adapt to those tasks and further improve performance, and a general class of such properties is the multiple reward…
Deep reinforcement learning (RL) can acquire complex behaviors from low-level inputs, such as images. However, real-world applications of such methods require generalizing to the vast variability of the real world. Deep networks are known…
Large-scale pre-trained Vision-Language Models (VLMs) have become essential for transfer learning across diverse tasks. However, adapting these models with limited few-shot data often leads to overfitting, diminishing their performance on…
A prevailing approach for learning visuomotor policies is to employ reinforcement learning to map high-dimensional visual observations directly to action commands. However, the combination of high-dimensional visual inputs and agile…
Applying reinforcement learning to robotic systems poses a number of challenging problems. A key requirement is the ability to handle continuous state and action spaces while remaining within a limited time and resource budget.…
Targets search and detection encompasses a variety of decision problems such as coverage, surveillance, search, observing and pursuit-evasion along with others. In this paper we develop a multi-agent deep reinforcement learning (MADRL)…
This study presents a benchmark for evaluating action-constrained reinforcement learning (RL) algorithms. In action-constrained RL, each action taken by the learning system must comply with certain constraints. These constraints are crucial…
Potential Based Reward Shaping combined with a potential function based on appropriately defined abstract knowledge has been shown to significantly improve learning speed in Reinforcement Learning. MultiGrid Reinforcement Learning (MRL) has…
While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…