相关论文: SoftDICE for Imitation Learning: Rethinking Off-po…

When performing imitation learning from expert demonstrations, distribution matching is a popular approach, in which one alternates between estimating distribution ratios and then using these ratios as rewards in a standard reinforcement…

In offline reinforcement learning, deriving an effective policy from a pre-collected set of experiences is challenging due to the distribution mismatch between the target policy and the behavioral policy used to collect the data, as well as…

Offline imitation learning (IL) promises the ability to learn performant policies from pre-collected demonstrations without interactions with the environment. However, imitating behaviors fully offline typically requires numerous expert…

We present GradientDICE for estimating the density ratio between the state distribution of the target policy and the sampling distribution in off-policy reinforcement learning. GradientDICE fixes several problems of GenDICE (Zhang et al.,…

Offline Reinforcement Learning (RL) is an emerging field of RL in which policies are learned solely from demonstrations. Within offline RL, some environments involve balancing multiple objectives, but existing multi-objective offline RL…

In the unsupervised pre-training for reinforcement learning, the agent aims to learn a prior policy for downstream tasks without relying on task-specific reward functions. We focus on state entropy maximization (SEM), where the goal is to…

We consider the problem of learning from observation (LfO), in which the agent aims to mimic the expert's behavior from the state-only demonstrations by experts. We additionally assume that the agent cannot interact with the environment but…

We study high-confidence behavior-agnostic off-policy evaluation in reinforcement learning, where the goal is to estimate a confidence interval on a target policy's value, given only access to a static experience dataset collected by…

In many real-world reinforcement learning applications, access to the environment is limited to a fixed dataset, instead of direct (online) interaction with the environment. When using this data for either evaluation or training of a new…

Offline imitation learning (IL) refers to learning expert behavior solely from demonstrations, without any additional interaction with the environment. Despite significant advances in offline IL, existing techniques find it challenging to…

We propose State Matching Offline DIstribution Correction Estimation (SMODICE), a novel and versatile regression-based offline imitation learning (IL) algorithm derived via state-occupancy matching. We show that the SMODICE objective admits…

The presence of uncertainty in policy evaluation significantly complicates the process of policy ranking and selection in real-world settings. We formally consider offline policy selection as learning preferences over a set of policy…

We study the problem of smooth imitation learning for online sequence prediction, where the goal is to train a policy that can smoothly imitate demonstrated behavior in a dynamic and continuous environment in response to online, sequential…

We consider the offline reinforcement learning (RL) setting where the agent aims to optimize the policy solely from the data without further environment interactions. In offline RL, the distributional shift becomes the primary source of…

Multi-objective reinforcement learning (MORL) aims to optimize policies in the presence of conflicting objectives, where linear scalarization is commonly used to reduce vector-valued returns into scalar signals. While effective for certain…

We study offline imitation learning (IL) in cooperative multi-agent settings, where demonstrations have unlabeled mixed quality - containing both expert and suboptimal trajectories. Our proposed solution is structured in two stages:…

Imitation learning is a central problem in reinforcement learning where the goal is to learn a policy that mimics the expert's behavior. In practice, it is often challenging to learn the expert policy from a limited number of demonstrations…

In this paper, we introduce MAAD, a novel, sample-efficient on-policy algorithm for Imitation Learning from Observations. MAAD utilizes a surrogate reward signal, which can be derived from various sources such as adversarial games,…

Large scale reinforcement learning has become a central tool for improving reasoning in large language models. At this scale, generation is often lagged or asynchronous, so updates are performed on data collected by older policies. This…

Diffusion policies have achieved superior performance in imitation learning and offline reinforcement learning (RL) due to their rich expressiveness. However, the conventional diffusion training procedure requires samples from target…