相关论文: Extrapolating Beyond Suboptimal Demonstrations via…

Inverse Reinforcement Learning (IRL) is a powerful paradigm for inferring a reward function from expert demonstrations. Many IRL algorithms require a known transition model and sometimes even a known expert policy, or they at least require…

We present an algorithm for Inverse Reinforcement Learning (IRL) from expert state observations only. Our approach decouples reward modelling from policy learning, unlike state-of-the-art adversarial methods which require updating the…

Imitation learning holds tremendous promise in learning policies efficiently for complex decision making problems. Current state-of-the-art algorithms often use inverse reinforcement learning (IRL), where given a set of expert…

Inverse reinforcement learning (IRL) is used to infer the reward function from the actions of an expert running a Markov Decision Process (MDP). A novel approach using variational inference for learning the reward function is proposed in…

We study the inverse reinforcement learning (IRL) problem under a transition dynamics mismatch between the expert and the learner. Specifically, we consider the Maximum Causal Entropy (MCE) IRL learner model and provide a tight upper bound…

Offline inverse reinforcement learning (Offline IRL) aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of…

Reinforcement Learning (RL) struggles in problems with delayed rewards, and one approach is to segment the task into sub-tasks with incremental rewards. We propose a framework called Hierarchical Inverse Reinforcement Learning (HIRL), which…

Inverse reinforcement learning (IRL) aims to infer rewards from observed behavior, but rewards are not identified from the policy alone: many reward--value pairs can rationalize the same actions. Meaningful reward recovery therefore…

Research on Inverse Reinforcement Learning (IRL) from third-person videos has shown encouraging results on removing the need for manual reward design for robotic tasks. However, most prior works are still limited by training from a…

We investigate the visual cross-embodiment imitation setting, in which agents learn policies from videos of other agents (such as humans) demonstrating the same task, but with stark differences in their embodiments -- shape, actions,…

Reinforcement learning (RL) has achieved tremendous success as a general framework for learning how to make decisions. However, this success relies on the interactive hand-tuning of a reward function by RL experts. On the other hand,…

Existing approaches to reward inference from behavior typically assume that humans provide demonstrations according to specific models of behavior. However, humans often indicate their goals through a wide range of behaviors, from actions…

Learning to imitate expert behavior from demonstrations can be challenging, especially in environments with high-dimensional, continuous observations and unknown dynamics. Supervised learning methods based on behavioral cloning (BC) suffer…

Meta-reinforcement learning (meta-RL) aims to learn from multiple training tasks the ability to adapt efficiently to unseen test tasks. Despite the success, existing meta-RL algorithms are known to be sensitive to the task distribution…

In reinforcement learning, Reverse Experience Replay (RER) is a recently proposed algorithm that attains better sample complexity than the classic experience replay method. RER requires the learning algorithm to update the parameters…

Not until recently, robust robot locomotion has been achieved by deep reinforcement learning (DRL). However, for efficient learning of parametrized bipedal walking, developed references are usually required, limiting the performance to that…

Inverse Reinforcement Learning infers a reward function from expert demonstrations, aiming to encode the behavior and intentions of the expert. Current approaches usually do this with generative and uni-modal models, meaning that they…

As generative agents become increasingly capable, alignment of their behavior with complex human values remains a fundamental challenge. Existing approaches often simplify human intent through reduction to a scalar reward, overlooking the…

Inverse Reinforcement Learning (RL) can be used to determine the behavior of Space Objects (SOs) by estimating the reward function that an SO is using for control. The approach discussed in this work can be used to analyze maneuvering of…

Reinforcement learning with offline data suffers from Q-value extrapolation errors. To address this issue, we first demonstrate that linear extrapolation of the Q-function beyond the data range is particularly problematic. To mitigate this,…