相关论文: Equivariant Data Augmentation for Generalization i…

Deep reinforcement learning (RL) agents often fail to generalize to unseen scenarios, even when they are trained on many instances of semantically similar environments. Data augmentation has recently been shown to improve the sample…

Offline reinforcement learning (RL) presents distinct challenges as it relies solely on observational data. A central concern in this context is ensuring the safety of the learned policy by quantifying uncertainties associated with various…

End-to-end learning robotic manipulation with high data efficiency is one of the key challenges in robotics. The latest methods that utilize human demonstration data and unsupervised representation learning has proven to be a promising…

Sample efficiency is critical when applying learning-based methods to robotic manipulation due to the high cost of collecting expert demonstrations and the challenges of on-robot policy learning through online Reinforcement Learning (RL).…

In this paper, we investigate offline reinforcement learning (RL) with the goal of training a single robust policy that generalizes effectively across environments with unseen dynamics. We propose a novel approach, Trajectory Encoding…

Offline reinforcement learning learns policies from fixed datasets without further environment interaction. A key challenge in this setting is epistemic uncertainty, arising from limited or biased data coverage, particularly when the…

Offline reinforcement learning (RL) is a learning paradigm where an agent learns from a fixed dataset of experience. However, learning solely from a static dataset can limit the performance due to the lack of exploration. To overcome it,…

Offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. The lack of environmental interactions makes the policy training vulnerable to state-action pairs far from the training…

In offline reinforcement learning (RL), we seek to utilize offline data to evaluate (or learn) policies in scenarios where the data are collected from a distribution that substantially differs from that of the target policy to be evaluated.…

Offline reinforcement learning (RL) learns policies entirely from static datasets, thereby avoiding the challenges associated with online data collection. Practical applications of offline RL will inevitably require learning from datasets…

Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same time minimizing the deviation from the behavior policy so as to…

Offline Reinforcement Learning (RL) aims to turn large datasets into powerful decision-making engines without any online interactions with the environment. This great promise has motivated a large amount of research that hopes to replicate…

This paper investigates a hybrid learning framework for reinforcement learning (RL) in which the agent can leverage both an offline dataset and online interactions to learn the optimal policy. We present a unified algorithm and analysis and…

The offline reinforcement learning (RL) paradigm provides a general recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data. While policy constraints, conservatism, and other…

The recent success of supervised learning methods on ever larger offline datasets has spurred interest in the reinforcement learning (RL) field to investigate whether the same paradigms can be translated to RL algorithms. This research…

Learning a goal-oriented dialog policy is generally performed offline with supervised learning algorithms or online with reinforcement learning (RL). Additionally, as companies accumulate massive quantities of dialog transcripts between…

Offline Reinforcement Learning (RL) is a promising approach for learning optimal policies in environments where direct exploration is expensive or unfeasible. However, the adoption of such policies in practice is often challenging, as they…

Generalization in Reinforcement Learning (RL) aims to learn an agent during training that generalizes to the target environment. This paper studies RL generalization from a theoretical aspect: how much can we expect pre-training over…

Interacting with the actual environment to acquire data is often costly and time-consuming in robotic tasks. Model-based offline reinforcement learning (RL) provides a feasible solution. On the one hand, it eliminates the requirements of…

Offline reinforcement learning (RL) aims to optimize the return given a fixed dataset of agent trajectories without additional interactions with the environment. While algorithm development has progressed rapidly, significant theoretical…