Related papers: Generalization of Compositional Tasks with Logical…

The ability to plan with temporal abstractions is central to intelligent decision-making. Rather than reasoning over primitive actions, we study agents that compose pre-trained policies as temporally extended actions, enabling solutions to…

Among various branches of offline reinforcement learning (RL) methods, goal-conditioned supervised learning (GCSL) has gained increasing popularity as it formulates the offline RL problem as a sequential modeling task, therefore bypassing…

Humanoid robots must master numerous tasks with sparse rewards, posing a challenge for reinforcement learning (RL). We propose a method combining RL and automated planning to address this. Our approach uses short goal-conditioned policies…

Reinforcement Learning (RL) has made significant strides in enabling artificial agents to learn diverse behaviors. However, learning an effective policy often requires a large number of environment interactions. To mitigate sample…

While large language models (LLMs) demonstrate strong reasoning capabilities utilizing reinforcement learning (RL) with verifiable reward, whether large vision-language models (VLMs) can directly inherit such capabilities through similar…

LLMs have shown remarkable proficiency in general language understanding and reasoning. However, they consistently underperform in spatial reasoning that severely limits their application, particularly in embodied intelligence. Inspired by…

We study the problem of control synthesis for multi-agent systems, to achieve complex, high-level, long-term goals that are assigned to each agent individually. As the agents might not be capable of satisfying their respective goals by…

Offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. The lack of environmental interactions makes the policy training vulnerable to state-action pairs far from the training…

Rewriting logic is naturally concurrent: several subterms of the state term can be rewritten simultaneously. But state terms are global, which makes compositionality difficult to achieve. Compositionality here means being able to decompose…

We study the problem of plan synthesis for multi-agent systems, to achieve complex, high-level, long-term goals that are assigned to each agent individually. As the agents might not be capable of satisfying their respective goals by…

Large Language Models (LLMs) enable intelligent multi-robot collaboration but face fundamental trade-offs: open-loop methods that compile tasks into formal representations for external executors produce sound plans but lack adaptability in…

Transferring high-level knowledge from a source task to a target task is an effective way to expedite reinforcement learning (RL). For example, propositional logic and first-order logic have been used as representations of such knowledge.…

Improving sample efficiency is central to Reinforcement Learning (RL), especially in environments where the rewards are sparse. Some recent approaches have proposed to specify reward functions as manually designed or learned reward…

We propose a novel planning technique for satisfying tasks specified in temporal logic in partially revealed environments. We define high-level actions derived from the environment and the given task itself, and estimate how each action…

Large language models (LLMs) are commonly adapted for diverse downstream tasks via parameter-efficient fine-tuning techniques such as Low-Rank Adapters (LoRA). While adapters can be combined to handle multiple tasks separately, standard…

Tasks with complex temporal structures and long horizons pose a challenge for reinforcement learning agents due to the difficulty in specifying the tasks in terms of reward functions as well as large variances in the learning signals. We…

Offline goal-conditioned reinforcement learning (GCRL) is a practical reinforcement learning paradigm that aims to learn goal-conditioned policies from reward-free offline data. Despite recent advances in hierarchical architectures such as…

Recent advancements in large language models (LLMs) have enabled their use as agents for planning complex tasks. Existing methods typically rely on a thought-action-observation (TAO) process to enhance LLM performance, but these approaches…

Goal-Conditioned Reinforcement Learning (GCRL) can enable agents to spontaneously set diverse goals to learn a set of skills. Despite the excellent works proposed in various fields, reaching distant goals in temporally extended tasks…

Hierarchical reinforcement learning (HRL) learns to make decisions on multiple levels of temporal abstraction. A key challenge in HRL is that the low-level policy changes over time, making it difficult for the high-level policy to generate…