Related papers: Conservative Offline Distributional Reinforcement …
A key problem in off-policy Reinforcement Learning (RL) is the mismatch, or distribution shift, between the dataset and the distribution over states and actions visited by the learned policy. This problem is exacerbated in the fully offline…
Traditional offline reinforcement learning (RL) methods predominantly operate in a batch-constrained setting. This confines the algorithms to a specific state-action distribution present in the dataset, reducing the effects of…
We study an approach to offline reinforcement learning (RL) based on optimally solving finitely-represented MDPs derived from a static dataset of experience. This approach can be applied on top of any learned representation and has the…
Offline reinforcement learning (RL) is challenged by the distributional shift between learning policies and datasets. To address this problem, existing works mainly focus on designing sophisticated algorithms to explicitly or implicitly…
The performance of offline reinforcement learning (RL) is sensitive to the proportion of high-return trajectories in the offline dataset. However, in many simulation environments and real-world scenarios, there are large ratios of…
Despite notable successes of Reinforcement Learning (RL), the prevalent use of an online learning paradigm prevents its widespread adoption, especially in hazardous or costly scenarios. Offline RL has emerged as an alternative solution,…
In reinforcement learning (RL), function approximation errors are known to easily lead to the Q-value overestimations, thus greatly reducing policy performance. This paper presents a distributional soft actor-critic (DSAC) algorithm, which…
Action and observation delays commonly occur in many Reinforcement Learning applications, such as remote control scenarios. We study the anatomy of randomly delayed environments, and show that partially resampling trajectory fragments in…
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…
Distribution shift is a major obstacle in offline reinforcement learning, which necessitates minimizing the discrepancy between the learned policy and the behavior policy to avoid overestimating rare or unseen actions. Previous conservative…
Distributionally robust offline reinforcement learning (RL), which seeks robust policy training against environment perturbation by modeling dynamics uncertainty, calls for function approximations when facing large state-action spaces.…
Recent advances in batch (offline) reinforcement learning have shown promising results in learning from available offline data and proved offline reinforcement learning to be an essential toolkit in learning control policies in a model-free…
Offline reinforcement learning (RL) addresses the challenge of expensive and high-risk data exploration inherent in RL by pre-training policies on vast amounts of offline data, enabling direct deployment or fine-tuning in real-world…
Policy constraint methods in offline reinforcement learning employ additional regularization techniques to constrain the discrepancy between the learned policy and the offline dataset. However, these methods tend to result in overly…
Improving the sample efficiency of reinforcement learning algorithms requires effective exploration. Following the principle of $\textit{optimism in the face of uncertainty}$ (OFU), we train a separate exploration policy to maximize the…
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.…
Several recent works have proposed a class of algorithms for the offline reinforcement learning (RL) problem that we will refer to as return-conditioned supervised learning (RCSL). RCSL algorithms learn the distribution of actions…
Modern navigation algorithms based on deep reinforcement learning (RL) show promising efficiency and robustness. However, most deep RL algorithms operate in a risk-neutral manner, making no special attempt to shield users from relatively…
Training a game-playing reinforcement learning agent requires multiple interactions with the environment. Ignorant random exploration may cause a waste of time and resources. It's essential to alleviate such waste. As discussed in this…
In dynamic programming (DP) and reinforcement learning (RL), an agent learns to act optimally in terms of expected long-term return by sequentially interacting with its environment modeled by a Markov decision process (MDP). More generally…