相关论文: Understanding and Controlling a Maze-Solving Polic…

Making sophisticated, robust, and safe sequential decisions is at the heart of intelligent systems. This is especially critical for planning in complex multi-agent environments, where agents need to anticipate other agents' intentions and…

The ability to learn robust policies while generalizing over large discrete action spaces is an open challenge for intelligent systems, especially in noisy environments that face the curse of dimensionality. In this paper, we present a…

Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions, measuring and mitigating scheming requires different…

In multi-objective optimization, learning all the policies that reach Pareto-efficient solutions is an expensive process. The set of optimal policies can grow exponentially with the number of objectives, and recovering all solutions…

We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may…

Learning robot manipulation through deep reinforcement learning in environments with sparse rewards is a challenging task. In this paper we address this problem by introducing a notion of imaginary object goals. For a given manipulation…

The field of reinforcement learning (RL) is concerned with algorithms for learning optimal policies in unknown stochastic environments. Programmatic RL studies representations of policies as programs, meaning involving higher order…

Embodied artificial intelligence (AI) tasks shift from tasks focusing on internet images to active settings involving embodied agents that perceive and act within 3D environments. In this paper, we investigate the target-driven visual…

We address the problem of learning hierarchical deep neural network policies for reinforcement learning. In contrast to methods that explicitly restrict or cripple lower layers of a hierarchy to force them to use higher-level modulating…

Inspired by biological swarms, robotic swarms are envisioned to solve real-world problems that are difficult for individual agents. Biological swarms can achieve collective intelligence based on local interactions and simple rules; however,…

Target-driven visual navigation is a challenging problem that requires a robot to find the goal using only visual inputs. Many researchers have demonstrated promising results using deep reinforcement learning (deep RL) on various robotic…

The prediction of humans' short-term trajectories has advanced significantly with the use of powerful sequential modeling and rich environment feature extraction. However, long-term prediction is still a major challenge for the current…

The main novelty of the proposed approach is that it allows a robot to learn an end-to-end policy which can adapt to changes in the environment during execution. While goal conditioning of policies has been studied in the RL literature,…

We investigate mathematically the notion of incoherence: a structural issue with reinforcement learning policies derived by naive goal-conditioning of autoregressive models. We focus on the process of re-training models on their own…

In this paper, we present a reinforcement learning approach to designing a control policy for a "leader" agent that herds a swarm of "follower" agents, via repulsive interactions, as quickly as possible to a target probability distribution…

During the first step of practical reasoning, i.e. deliberation or goals selection, an intelligent agent generates a set of pursuable goals and then selects which of them he commits to achieve. Explainable Artificial Intelligence (XAI)…

Pursuit-evasion is the problem of capturing mobile targets with one or more pursuers. We use deep reinforcement learning for pursuing an omni-directional target with multiple, homogeneous agents that are subject to unicycle kinematic…

As the range of tasks performed by a general vision system expands, executing multiple tasks accurately and efficiently in a single network has become an important and still open problem. Recent computer vision approaches address this…

Learning new skills by observing humans' behaviors is an essential capability of AI. In this work, we leverage instructional videos to study humans' decision-making processes, focusing on learning a model to plan goal-directed actions in…

Generating robot motion that fulfills multiple tasks simultaneously is challenging due to the geometric constraints imposed by the robot. In this paper, we propose to solve multi-task problems through learning structured policies from human…