Related papers: Policy-Based Self-Competition for Planning Problem…

Large-scale AI systems that combine search and learning have reached super-human levels of performance in game-playing, but have also been shown to fail in surprising ways. The brittleness of such models limits their efficacy and…

Multi-agent football poses an unsolved challenge in AI research. Existing work has focused on tackling simplified scenarios of the game, or else leveraging expert demonstrations. In this paper, we develop a multi-agent system to play the…

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…

Recent progress in reinforcement learning (RL) using self-game-play has shown remarkable performance on several board games (e.g., Chess and Go) as well as video games (e.g., Atari games and Dota2). It is plausible to consider that RL,…

Search and planning algorithms have been a cornerstone of artificial intelligence since the field's inception. Giving reinforcement learning agents the ability to plan during execution time has resulted in significant performance…

The combination of Monte-Carlo Tree Search (MCTS) and deep reinforcement learning is state-of-the-art in two-player perfect-information games. In this paper, we describe a search algorithm that uses a variant of MCTS which we enhanced by 1)…

AlphaZero has achieved impressive performance in deep reinforcement learning by utilizing an architecture that combines search and training of a neural network in self-play. Many researchers are looking for ways to reproduce and improve…

Recent superhuman results in games have largely been achieved in a variety of zero-sum settings, such as Go and Poker, in which agents need to compete against others. However, just like humans, real-world AI systems have to coordinate and…

We study a setting in which a principal selects an agent to execute a collection of tasks according to a specified priority sequence. Agents, however, have their own individual priority sequences according to which they wish to execute the…

The combination of Monte-Carlo tree search (MCTS) with deep reinforcement learning has led to significant advances in artificial intelligence. However, AlphaZero, the current state-of-the-art MCTS algorithm, still relies on handcrafted…

Existing language agents often encounter difficulties in dynamic adversarial games due to poor strategic reasoning. To mitigate this limitation, a promising approach is to allow agents to learn from game interactions automatically, without…

We introduce a method based on the Public Goods Game for solving optimization tasks. In particular, we focus on the Traveling Salesman Problem, i.e. a NP-hard problem whose search space exponentially grows increasing the number of cities.…

General-purpose robots require diverse repertoires of behaviors to complete challenging tasks in real-world unstructured environments. To address this issue, goal-conditioned reinforcement learning aims to acquire policies that can reach…

Simultaneous AlphaZero extends the AlphaZero framework to multistep, two-player zero-sum deterministic Markov games with simultaneous actions. At each decision point, joint action selection is resolved via matrix games whose payoffs…

The success of AlphaZero (AZ) has demonstrated that neural-network-based Go AIs can surpass human performance by a large margin. Given that the state space of Go is extremely large and a human player can play the game from any legal state,…

A recursive tree planner (RTP) is designed to function as a pure planner without policies at one extreme and run a pure greedy policy at the other. In between, the RTP exploits policies to improve planning performance and improve zero-shot…

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…

Forecasting when AI systems will become capable of meaningfully accelerating AI research is a central challenge for AI safety. Existing benchmarks measure broad capability growth, but may not provide ample early warning signals for…

Autonomous vehicles (AVs) need to reason about the multimodal behavior of neighboring agents while planning their own motion. Many existing trajectory planners seek a single trajectory that performs well under \emph{all} plausible futures…

By introducing several improvements to the AlphaZero process and architecture, we greatly accelerate self-play learning in Go, achieving a 50x reduction in computation over comparable methods. Like AlphaZero and replications such as ELF…