Related papers: Beyond State Consistency: Behavior Consistency in …

Time-inconsistency is a characteristic of human behavior in which people plan for long-term benefits but take actions that differ from the plan due to conflicts with short-term benefits. Such time-inconsistent behavior is believed to be…

World models enable agents to plan by imagining future states, but existing approaches operate from a single viewpoint, typically egocentric, even when other perspectives would make planning easier; navigation, for instance, benefits from a…

Agents must infer action outcomes and select actions that maximize a reward signal indicating how close the goal is to being reached. Supervised learning of reward models could introduce biases inherent to training data, limiting…

Reinforcement learning methods require careful design involving a reward function to obtain the desired action policy for a given task. In the absence of hand-crafted reward functions, prior work on the topic has proposed several methods…

Multi-agent systems must decide which agent is the most appropriate for a given task. We propose a novel architecture for recommending which LLM agent out of many should perform a task given a natural language prompt by extending the…

Numerous offline and model-based reinforcement learning systems incorporate world models to emulate the inherent environments. A world model is particularly important in scenarios where direct interactions with the real environment is…

Large Language Models (LLMs) can serve as world models to enhance agent decision-making in digital environments by simulating future states and predicting action outcomes, potentially eliminating costly trial-and-error exploration. However,…

Solving multi-goal reinforcement learning (RL) problems with sparse rewards is generally challenging. Existing approaches have utilized goal relabeling on collected experiences to alleviate issues raised from sparse rewards. However, these…

We consider model-based reinforcement learning (MBRL) in 2-agent, high-fidelity continuous control problems -- an important domain for robots interacting with other agents in the same workspace. For non-trivial dynamical systems, MBRL…

Video world models have achieved strong visual realism, but this does not ensure that their dynamics are truly governed by actions. In this work, we argue that action faithfulness should be understood through the compositional structure of…

The utility of learning a dynamics/world model of the environment in reinforcement learning has been shown in a many ways. When using neural networks, however, these models suffer catastrophic forgetting when learned in a lifelong or…

Learned dynamics models combined with both planning and policy learning algorithms have shown promise in enabling artificial agents to learn to perform many diverse tasks with limited supervision. However, one of the fundamental challenges…

Time-series forecasting is crucial for numerous real-world applications including weather prediction and financial market modeling. While temporal-domain methods remain prevalent, frequency-domain approaches can effectively capture…

Generative Reward Models (GenRMs) and LLM-as-a-Judge exhibit deceptive alignment by producing correct judgments for incorrect reasons, as they are trained and evaluated to prioritize Outcome Accuracy, which undermines their ability to…

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

Learning physical dynamics in a series of non-stationary environments is a challenging but essential task for model-based reinforcement learning (MBRL) with visual inputs. It requires the agent to consistently adapt to novel tasks without…

Reward models have become a staple in modern NLP, serving as not only a scalable text evaluator, but also an indispensable component in many alignment recipes and inference-time algorithms. However, while recent reward models increase…

Learning world models offers a promising avenue for goal-conditioned reinforcement learning with sparse rewards. By allowing agents to plan actions or exploratory goals without direct interaction with the environment, world models enhance…

We formulate and study a general time-varying multi-agent system where players repeatedly compete under incomplete information. Our work is motivated by scenarios commonly observed in online advertising and retail marketplaces, where agents…

To solve control problems via model-based reasoning or planning, an agent needs to know how its actions affect the state of the world. The actions an agent has at its disposal often change the state of the environment in systematic ways.…