相关论文: Grounding LTL Tasks in Sub-Symbolic RL Environment…

Recent works successfully leveraged Large Language Models' (LLM) abilities to capture abstract knowledge about world's physics to solve decision-making problems. Yet, the alignment between LLMs' knowledge and the environment can be wrong…

We propose a framework that leverages foundation models as teachers, guiding a reinforcement learning agent to acquire semantically meaningful behavior without human feedback. In our framework, the agent receives task instructions grounded…

Linear temporal logic (LTL) has recently been adopted as a powerful formalism for specifying complex, temporally extended tasks in multi-task reinforcement learning (RL). However, learning policies that efficiently satisfy arbitrary…

In reinforcement learning (RL), continuing tasks refer to tasks where the agent-environment interaction is ongoing and can not be broken down into episodes. These tasks are suitable when environment resets are unavailable, agent-controlled,…

Reinforcement Learning (RL) based methods have been increasingly explored for robot learning. However, RL based methods often suffer from low sampling efficiency in the exploration phase, especially for long-horizon manipulation tasks, and…

We introduce a new RL problem where the agent is required to generalize to a previously-unseen environment characterized by a subtask graph which describes a set of subtasks and their dependencies. Unlike existing hierarchical multitask RL…

Reinforcement learning has been applied to many interesting problems such as the famous TD-gammon and the inverted helicopter flight. However, little effort has been put into developing methods to learn policies for complex persistent tasks…

Text-based games (TBG) have emerged as promising environments for driving research in grounded language understanding and studying problems like generalization and sample efficiency. Several deep reinforcement learning (RL) methods with…

Adapting to unforeseen novelties in open-world environments remains a major challenge for autonomous systems. While hybrid planning and reinforcement learning (RL) approaches show promise, they often suffer from sample inefficiency, slow…

Reinforcement Learning (RL) is a promising approach for solving various control, optimization, and sequential decision making tasks. However, designing reward functions for complex tasks (e.g., with multiple objectives and safety…

Although deep reinforcement learning has recently been very successful at learning complex behaviors, it requires a tremendous amount of data to learn a task. One of the fundamental reasons causing this limitation lies in the nature of the…

Large language models (LLMs) are becoming the foundation for autonomous agents that can use tools to solve complex tasks. Reinforcement learning (RL) has emerged as a common approach for injecting such agentic capabilities, but typically…

Directly training Large Language Models (LLMs) for Multi-Agent Systems (MAS) remains challenging due to intricate reward modeling, dynamic agent interactions, and demanding generalization requirements. This paper explores whether…

We examine five setups where an agent (or two agents) seeks to explore unknown environment without any prior information. Although seemingly very different, all of them can be formalized as Reinforcement Learning (RL) problems in hyperbolic…

Reinforcement learning (RL) is one of the active fields in machine learning, demonstrating remarkable potential in tackling real-world challenges. Despite its promising prospects, this methodology has encountered with issues and challenges,…

Generalizing to complex and temporally extended task objectives and safety constraints remains a critical challenge in reinforcement learning (RL). Linear temporal logic (LTL) offers a unified formalism to specify such requirements, yet…

Emergent symbolic representations are critical for enabling developmental learning agents to plan and generalize across tasks. In this work, we investigate whether large language models (LLMs) can translate human natural language…

Compositional reinforcement learning is a promising approach for training policies to perform complex long-horizon tasks. Typically, a high-level task is decomposed into a sequence of subtasks and a separate policy is trained to perform…

Reward-free reinforcement learning (RL) is a framework which is suitable for both the batch RL setting and the setting where there are many reward functions of interest. During the exploration phase, an agent collects samples without using…

Deep reinforcement learning provides a promising approach for text-based games in studying natural language communication between humans and artificial agents. However, the generalization still remains a big challenge as the agents depend…