相关论文: Model-based Offline Reinforcement Learning with Lo…
Online reinforcement learning (RL) methods are often data-inefficient or unreliable, making them difficult to train on real robotic hardware, especially quadruped robots. Learning robotic tasks from pre-collected data is a promising…
Offline multi-agent reinforcement learning is challenging due to the coupling effect of both distribution shift issue common in offline setting and the high dimension issue common in multi-agent setting, making the action…
A compelling use case of offline reinforcement learning (RL) is to obtain a policy initialization from existing datasets followed by fast online fine-tuning with limited interaction. However, existing offline RL methods tend to behave…
Model-based offline reinforcement learning (RL) aims to enhance offline RL with a dynamics model that facilitates policy exploration. However, \textit{model exploitation} could occur due to inevitable model errors, degrading algorithm…
We study offline reinforcement learning of style-conditioned policies using explicit style supervision via subtrajectory labeling functions. In this setting, aligning style with high task performance is particularly challenging due to…
We propose a novel offline reinforcement learning (offline RL) approach, introducing the Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation (DIAR) framework. We address two key challenges in offline RL: out-of-distribution…
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.…
Model-based reinforcement learning (RL) has shown great promise due to its sample efficiency, but still struggles with long-horizon sparse-reward tasks, especially in offline settings where the agent learns from a fixed dataset. We…
Offline reinforcement learning (RL) defines the task of learning from a fixed batch of data. Due to errors in value estimation from out-of-distribution actions, most offline RL algorithms take the approach of constraining or regularizing…
Offline reinforcement learning (offline RL) offers a promising framework for developing control strategies in chemical process systems using historical data, without the risks or costs of online experimentation. This work investigates the…
Offline reinforcement learning aims to train agents from pre-collected datasets. However, this comes with the added challenge of estimating the value of behaviors not covered in the dataset. Model-based methods offer a potential solution by…
Training offline RL models using visual inputs poses two significant challenges, i.e., the overfitting problem in representation learning and the overestimation bias for expected future rewards. Recent work has attempted to alleviate the…
Offline reinforcement learning (RL) seeks to learn optimal policies from static datasets without interacting with the environment. A common challenge is handling multi-modal action distributions, where multiple behaviours are represented in…
We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common representation and is asked to learn the shared representation.…
We consider reinforcement learning (RL) methods in offline domains without additional online data collection, such as mobile health applications. Most of existing policy optimization algorithms in the computer science literature are…
Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction. It addresses challenges with regard to the cost of data…
Offline reinforcement learning (RL) methods strike a balance between exploration and exploitation by conservative value estimation -- penalizing values of unseen states and actions. Model-free methods penalize values at all unseen actions,…
Offline reinforcement learning (RL) promises the ability to learn effective policies solely using existing, static datasets, without any costly online interaction. To do so, offline RL methods must handle distributional shift between the…
The objective of offline RL is to learn optimal policies when a fixed exploratory demonstrations data-set is available and sampling additional observations is impossible (typically if this operation is either costly or rises ethical…
In offline reinforcement learning (RL), the goal is to learn a highly rewarding policy based solely on a dataset of historical interactions with the environment. The ability to train RL policies offline can greatly expand the applicability…