相关论文: UniZero: Generalized and Efficient Planning with S…

In heterogeneous multi-task decision-making, tasks not only exhibit diverse observation and action spaces but also vary substantially in their underlying complexities. While conventional multi-task world models like UniZero excel in…

Planning with options -- a sequence of primitive actions -- has been shown effective in reinforcement learning within complex environments. Previous studies have focused on planning with predefined options or learned options through expert…

Leveraging the rich world knowledge of Large Language Models (LLMs) to enhance Reinforcement Learning (RL) agents offers a promising path toward general intelligence. However, a fundamental prior-dynamics mismatch hinders existing…

Building agents based on tree-search planning capabilities with learned models has achieved remarkable success in classic decision-making problems, such as Go and Atari. However, it has been deemed challenging or even infeasible to extend…

Model-based planning is often thought to be necessary for deep, careful reasoning and generalization in artificial agents. While recent successes of model-based reinforcement learning (MBRL) with deep function approximation have…

Constructing agents with planning capabilities has long been one of the main challenges in the pursuit of artificial intelligence. Tree-based planning methods have enjoyed huge success in challenging domains, such as chess and Go, where a…

We present TransZero, a model-based reinforcement learning algorithm that removes the sequential bottleneck in Monte Carlo Tree Search (MCTS). Unlike MuZero, which constructs its search tree step by step using a recurrent dynamics model,…

Deep reinforcement learning repeatedly succeeds in closed, well-defined domains such as games (Chess, Go, StarCraft). The next frontier is real-world scenarios, where setups are numerous and varied. For this, agents need to learn the…

The idea of decision-aware model learning, that models should be accurate where it matters for decision-making, has gained prominence in model-based reinforcement learning. While promising theoretical results have been established, the…

Many important real-world problems have action spaces that are high-dimensional, continuous or both, making full enumeration of all possible actions infeasible. Instead, only small subsets of actions can be sampled for the purpose of policy…

Learning efficiently from small amounts of data has long been the focus of model-based reinforcement learning, both for the online case when interacting with the environment and the offline case when learning from a fixed dataset. However,…

Model-based reinforcement learning (MBRL) has drawn considerable interest in recent years, given its promise to improve sample efficiency. Moreover, when using deep-learned models, it is possible to learn compact and generalizable models…

Decision-making agents with planning capabilities have achieved huge success in the challenging domain like Chess, Shogi, and Go. In an effort to generalize the planning ability to the more general tasks where the environment dynamics are…

World model emerges as a key module in decision making, where MuZero and Dreamer achieve remarkable successes in complex tasks. Recent work leverages Large Language Models (LLMs) as general world simulators to simulate the dynamics of the…

MuZero, a model-based reinforcement learning algorithm that uses a value equivalent dynamics model, achieved state-of-the-art performance in Chess, Shogi and the game of Go. In contrast to standard forward dynamics models that predict a…

MuZero has achieved superhuman performance in various games by using a dynamics network to predict the environment dynamics for planning, without relying on simulators. However, the latent states learned by the dynamics network make its…

Monte Carlo Tree Search (MCTS) has proven highly effective in solving complex planning tasks by balancing exploration and exploitation using Upper Confidence Bound for Trees (UCT). However, existing work have not considered MCTS-based…

MuZero Unplugged presents a promising approach for offline policy learning from logged data. It conducts Monte-Carlo Tree Search (MCTS) with a learned model and leverages Reanalyze algorithm to learn purely from offline data. For good…

The uncertainty of distributed renewable energy brings significant challenges to economic operation of microgrids. Conventional online optimization approaches require a forecast model. However, accurately forecasting the renewable power…

In this paper, we introduce ObjectZero, a novel reinforcement learning (RL) algorithm that leverages the power of object-level representations to model dynamic environments more effectively. Unlike traditional approaches that process the…