Related papers: Physical Reasoning Using Dynamics-Aware Models

Service robots can help with many of our daily tasks, especially in those cases where it is inconvenient or unsafe for us to intervene: e.g., under extreme weather conditions or when social distance needs to be maintained. However, before…

To perform robot manipulation tasks, a low-dimensional state of the environment typically needs to be estimated. However, designing a state estimator can sometimes be difficult, especially in environments with deformable objects. An…

When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task -- the task ``features" -- as well as how to combine these features…

The aim of Reinforcement Learning (RL) in real-world applications is to create systems capable of making autonomous decisions by learning from their environment through trial and error. This paper emphasizes the importance of reward…

Reward shaping is an effective technique for incorporating domain knowledge into reinforcement learning (RL). Existing approaches such as potential-based reward shaping normally make full use of a given shaping reward function. However,…

Recent successes of reinforcement learning (RL) in training large reasoning models motivate the question of whether self-training - the process where a model learns from its own judgments - can be sustained within RL. In this work, we study…

Reinforcement learning problems are often described through rewards that indicate if an agent has completed some task. This specification can yield desirable behavior, however many problems are difficult to specify in this manner, as one…

Recent work in reinforcement learning has leveraged symmetries in the model to improve sample efficiency in training a policy. A commonly used simplifying assumption is that the dynamics and reward both exhibit the same symmetry; however,…

Humans are interactive agents driven to seek out situations with interesting physical dynamics. Here we formalize the functional form of physical intrinsic motivation. We first collect ratings of how interesting humans find a variety of…

Action-conditioned robot world models generate future video frames of the manipulated scene given a robot action sequence, offering a promising alternative for simulating tasks that are difficult to model with traditional physics engines.…

While reinforcement learning (RL) demonstrated remarkable success in enhancing the reasoning capabilities of language models, the training dynamics of RL in LLMs remain unclear. In this work, we provide an explanation of the RL training…

Our goal in this paper is to plan the motion of a robot in a partitioned environment with dynamically changing, locally sensed rewards. We assume that arbitrary assumptions on the reward dynamics can be given. The robot aims to accomplish a…

In this paper we address the problem of visual reaction: the task of interacting with dynamic environments where the changes in the environment are not necessarily caused by the agent itself. Visual reaction entails predicting the future…

Reinforcement learning has advanced video reasoning in large multi-modal models, yet dominant pipelines either rely on on-policy self-exploration, which plateaus at the model's knowledge boundary, or hybrid replay that mixes policies and…

The focus of this paper is to propose a driver model that incorporates human reasoning levels as actions during interactions with other drivers. Different from earlier work using game theoretical human reasoning levels, we propose a dynamic…

Autonomous robots operating in open and changing environments cannot always rely on predefined inputs, outputs, and action routines. Although existing learning methods enable robots to improve their performance through environmental…

Reinforcement learning agents are fundamentally limited by the quality of the reward functions they learn from, yet reward design is often overlooked under the assumption that a well-defined reward is readily available. However, in…

Reinforcement learning (RL) is an effective approach to motion planning in autonomous driving, where an optimal driving policy can be automatically learned using the interaction data with the environment. Nevertheless, the reward function…

Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered…

The interpretation of spatial references is highly contextual, requiring joint inference over both language and the environment. We consider the task of spatial reasoning in a simulated environment, where an agent can act and receive…