Related papers: TOP-ERL: Transformer-based Off-Policy Episodic Rei…
The rising successes of RL are propelled by combining smart algorithmic strategies and deep architectures to optimize the distribution of returns and visitations over the state-action space. A quantitative framework to compare the learning…
Adversarial Imitation Learning (AIL) is a class of algorithms in Reinforcement learning (RL), which tries to imitate an expert without taking any reward from the environment and does not provide expert behavior directly to the policy…
System optimal traffic routing can mitigate congestion by assigning routes for a portion of vehicles so that the total travel time of all vehicles in the transportation system can be reduced. However, achieving real-time optimal routing…
Off-policy reinforcement learning has many applications including: learning from demonstration, learning multiple goal seeking policies in parallel, and representing predictive knowledge. Recently there has been an proliferation of new…
We present a data-efficient framework for solving sequential decision-making problems which exploits the combination of reinforcement learning (RL) and latent variable generative models. The framework, called GenRL, trains deep policies by…
Empowered by deep neural networks, deep reinforcement learning (DRL) has demonstrated tremendous empirical successes in various domains, including games, health care, and autonomous driving. Despite these advancements, DRL is still…
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 widely-studied deep reinforcement learning (RL) technique known as Prioritized Experience Replay (PER) allows agents to learn from transitions sampled with non-uniform probability proportional to their temporal-difference (TD) error.…
Reinforcement Learning (RL) based methods have been increasingly explored for robot learning. However, RL based methods often suffer from low sampling efficiency in the exploration phase, especially for long-horizon manipulation tasks, and…
Meta-reinforcement learning (RL) methods can meta-train policies that adapt to new tasks with orders of magnitude less data than standard RL, but meta-training itself is costly and time-consuming. If we can meta-train on offline data, then…
Learning complex policies with Reinforcement Learning (RL) is often hindered by instability and slow convergence, a problem exacerbated by the difficulty of reward engineering. Imitation Learning (IL) from expert demonstrations bypasses…
Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to the inherent distributional shift and value function…
Large transformer models powered by diverse data and model scale have dominated natural language modeling and computer vision and pushed the frontier of multiple AI areas. In reinforcement learning (RL), despite many efforts into…
Off-policy reinforcement learning (RL) has achieved notable success in tackling many complex real-world tasks, by leveraging previously collected data for policy learning. However, most existing off-policy RL algorithms fail to maximally…
Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…
Behavior constrained policy optimization has been demonstrated to be a successful paradigm for tackling Offline Reinforcement Learning. By exploiting historical transitions, a policy is trained to maximize a learned value function while…
Reinforcement learning (RL) is typically concerned with estimating stationary policies or single-step models, leveraging the Markov property to factorize problems in time. However, we can also view RL as a generic sequence modeling problem,…
We study the offline meta-reinforcement learning (OMRL) problem, a paradigm which enables reinforcement learning (RL) algorithms to quickly adapt to unseen tasks without any interactions with the environments, making RL truly practical in…
Learning robot control policies from demonstrations is a powerful paradigm, yet real-world data is often suboptimal, noisy, or otherwise imperfect, posing significant challenges for imitation and reinforcement learning. In this work, we…
Maximum entropy has become a mainstream off-policy reinforcement learning (RL) framework for balancing exploitation and exploration. However, two bottlenecks still limit further performance improvement: (1) non-stationary Q-value estimation…