English
Related papers

Related papers: LobsDICE: Offline Learning from Observation via St…

200 papers

Imitation Learning from Observation (ILfO) is a setting in which a learner tries to imitate the behavior of an expert, using only observational data and without the direct guidance of demonstrated actions. In this paper, we re-examine…

Robotics · Computer Science 2024-10-07 Wei-Di Chang , Scott Fujimoto , David Meger , Gregory Dudek

We study a new paradigm for sequential decision making, called offline policy learning from observations (PLfO). Offline PLfO aims to learn policies using datasets with substandard qualities: 1) only a subset of trajectories is labeled with…

Machine Learning · Computer Science 2023-08-08 Anqi Li , Byron Boots , Ching-An Cheng

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…

Machine Learning · Computer Science 2024-12-10 Catalin E. Brita , Stephan Bongers , Frans A. Oliehoek

Learning from demonstration (LfD) is the process of building behavioral models of a task from demonstrations provided by an expert. These models can be used e.g. for system control by generalizing the expert demonstrations to previously…

Machine Learning · Statistics 2017-08-07 Adrian Šošić , Abdelhak M. Zoubir , Heinz Koeppl

Demonstrations are an effective alternative to task specification for learning agents in settings where designing a reward function is difficult. However, demonstrating expert behavior in the action space of the agent becomes unwieldy when…

Machine Learning · Computer Science 2024-09-23 Harshit Sikchi , Caleb Chuck , Amy Zhang , Scott Niekum

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…

Machine Learning · Computer Science 2019-12-12 Ilya Kostrikov , Ofir Nachum , Jonathan Tompson

We address the challenge of offline reinforcement learning using realistic data, specifically non-expert data collected through sub-optimal behavior policies. Under such circumstance, the learned policy must be safe enough to manage…

Machine Learning · Computer Science 2025-04-04 Ke Jiang , Wen Jiang , Yao Li , Xiaoyang Tan

Distribution shift in imitation learning refers to the problem that the agent cannot plan proper actions for a state that has not been visited during the training. This problem can be largely attributed to the inherently narrow state-action…

Robotics · Computer Science 2026-05-26 Hyung-Suk Yoon , Seung-Woo Seo

An important problem that arises in reinforcement learning and Monte Carlo methods is estimating quantities defined by the stationary distribution of a Markov chain. In many real-world applications, access to the underlying transition…

Machine Learning · Statistics 2020-02-24 Ruiyi Zhang , Bo Dai , Lihong Li , Dale Schuurmans

The deployment of Reinforcement Learning to robotics applications faces the difficulty of reward engineering. Therefore, approaches have focused on creating reward functions by Learning from Observations (LfO) which is the task of learning…

Robotics · Computer Science 2023-03-07 Milan Ganai , Chiaki Hirayama , Ya-Chien Chang , Sicun Gao

We study off-dynamics offline reinforcement learning, where the goal is to learn a policy from offline source and limited target datasets with mismatched dynamics. Existing methods either penalize the reward or discard source transitions…

Machine Learning · Computer Science 2026-03-19 Yihong Guo , Yu Yang , Pan Xu , Anqi Liu

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…

Machine Learning · Computer Science 2025-12-12 Jongmin Lee , Meiqi Sun , Pieter Abbeel

We focus on the problem of imitation learning from visual observations, where the learning agent has access to videos of experts as its sole learning source. The challenges of this framework include the absence of expert actions and the…

Machine Learning · Computer Science 2024-05-27 Vittorio Giammarino , James Queeney , Ioannis Ch. Paschalidis

Imitation Learning from observation describes policy learning in a similar way to human learning. An agent's policy is trained by observing an expert performing a task. While many state-only imitation learning approaches are based on…

Machine Learning · Computer Science 2024-10-02 Damian Boborzi , Christoph-Nikolas Straehle , Jens S. Buchner , Lars Mikelsons

Learning from visual observation (LfVO), aiming at recovering policies from only visual observation data, is promising yet a challenging problem. Existing LfVO approaches either only adopt inefficient online learning schemes or require…

Machine Learning · Computer Science 2023-06-23 Bohan Zhou , Ke Li , Jiechuan Jiang , Zongqing Lu

Imitation from observation is a computational technique that teaches an agent on how to mimic the behavior of an expert by observing only the sequence of states from the expert demonstrations. Recent approaches learn the inverse dynamics of…

Artificial Intelligence · Computer Science 2020-04-29 Juarez Monteiro , Nathan Gavenski , Roger Granada , Felipe Meneguzzi , Rodrigo Barros

In this paper, we describe a novel approach to imitation learning that infers latent policies directly from state observations. We introduce a method that characterizes the causal effects of latent actions on observations while…

Machine Learning · Computer Science 2019-05-14 Ashley D. Edwards , Himanshu Sahni , Yannick Schroecker , Charles L. Isbell

Learning from Demonstrations (LfD) via Behavior Cloning (BC) works well on multiple complex tasks. However, a limitation of the typical LfD approach is that it requires expert demonstrations for all scenarios, including those in which the…

Robotics · Computer Science 2019-12-06 Jing Bi , Vikas Dhiman , Tianyou Xiao , Chenliang Xu

Limited data has become a major bottleneck in scaling up offline imitation learning (IL). In this paper, we propose enhancing IL performance under limited expert data by introducing a pre-training stage that learns dynamics representations,…

Robotics · Computer Science 2025-08-21 Haitong Ma , Bo Dai , Zhaolin Ren , Yebin Wang , Na Li

Stationary Distribution Correction Estimation (DICE) addresses the mismatch between the stationary distribution induced by a policy and the target distribution required for reliable off-policy evaluation (OPE) and policy optimization.…

Machine Learning · Computer Science 2025-06-11 Woosung Kim , JunHo Seo , Jongmin Lee , Byung-Jun Lee