Related papers: Reinforcement Learning with Inverse Rewards for Wo…

Large language models (LLMs) trained via pretraining and supervised fine-tuning (SFT) can still produce harmful and misaligned outputs, or struggle in domains like math and coding. Reinforcement learning (RL)-based post-training methods,…

How well do reward functions learned with inverse reinforcement learning (IRL) generalize? We illustrate that state-of-the-art IRL algorithms, which maximize a maximum-entropy objective, learn rewards that overfit to the demonstrations.…

Inverse Reinforcement Learning (IRL) has demonstrated effectiveness in a variety of imitation tasks. In this paper, we introduce an IRL framework designed to extract rewarding features from expert trajectories affected by delayed…

We study the problem of generalizing an expert agent's behavior, provided through demonstrations, to new environments and/or additional constraints. Inverse Reinforcement Learning (IRL) offers a promising solution by seeking to recover the…

Learning from few demonstrations to develop policies robust to variations in robot initial positions and object poses is a problem of significant practical interest in robotics. Compared to imitation learning, which often struggles to…

Inverse reinforcement learning (IRL) is the problem of finding a reward function that generates a given optimal policy for a given Markov Decision Process. This paper looks at an algorithmic-independent geometric analysis of the IRL problem…

We propose an inverse reinforcement learning (IRL) approach using Deep Q-Networks to extract the rewards in problems with large state spaces. We evaluate the performance of this approach in a simulation-based autonomous driving scenario.…

Reinforcement learning (RL) requires skillful definition and remarkable computational efforts to solve optimization and control problems, which could impair its prospect. Introducing human guidance into reinforcement learning is a promising…

Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy. However, these methods suffer from sparse and unstable reward signals returned by a user simulator only when a…

Inverse Reinforcement Learning (IRL) learns an optimal policy, given some expert demonstrations, thus avoiding the need for the tedious process of specifying a suitable reward function. However, current methods are constrained by at least…

Reinforcement Learning (RL) applications in real-world scenarios must prioritize safety and reliability, which impose strict constraints on agent behavior. Model-based RL leverages predictive world models for action planning and policy…

Video diffusion models have made rapid progress in perceptual realism and temporal coherence, but they remain primarily optimized for plausible generation rather than verifiable reasoning. This limitation is especially pronounced in tasks…

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…

In the search for more sample-efficient reinforcement-learning (RL) algorithms, a promising direction is to leverage as much external off-policy data as possible. For instance, expert demonstrations. In the past, multiple ideas have been…

Video generation models trained on heterogeneous data with likelihood-surrogate objectives can produce visually plausible rollouts that violate physical constraints in embodied manipulation. Although reinforcement-learning post-training…

Imitation by observation is an approach for learning from expert demonstrations that lack action information, such as videos. Recent approaches to this problem can be placed into two broad categories: training dynamics models that aim to…

Reinforcement Learning with Verifiable Rewards (RLVR) has been an effective approach for improving Large Language Models' reasoning in domains such as coding and mathematics. Here, we apply RLVR methods towards forecasting future real-world…

An inverse reinforcement learning (IRL) agent learns to act intelligently by observing expert demonstrations and learning the expert's underlying reward function. Although learning the reward functions from demonstrations has achieved great…

Scaling model-based inverse reinforcement learning (IRL) to real robotic manipulation tasks with unknown dynamics remains an open problem. The key challenges lie in learning good dynamics models, developing algorithms that scale to…

Interactive reinforcement learning can effectively facilitate the agent training via human feedback. However, such methods often require the human teacher to know what is the correct action that the agent should take. In other words, if the…