arXiv research

eva method improves RL models by adaptively creating prompts, boosting performance.

In hierarchical reinforcement learning a major challenge is determining appropriate low-level policies. We propose an unsupervised learning scheme, based on asymmetric self-play from Sukhbaatar et al. (2018), that automatically learns a good representation of sub-goals in the environment and a low-level policy that can…

Self-play is an unsupervised training procedure which enables the reinforcement learning agents to explore the environment without requiring any external rewards. We augment the self-play setting by providing an external memory where the agent can store experience from the previous tasks. This enables the agent to come…

Automatically finds effective security strategies through reinforcement learning and self-play.

New algorithms prove self-play can be effective in competitive RL.

This paper improves self-play learning in games by manipulating experience distributions.

Framework improves self-play for cooperative multi-agent learning.

The paper investigates how supervised learning and self-play improve sample efficiency in teaching AI to communicate.

AlphaZero's reward function is replaced with a total ordering, enabling self-play without balancing.

New algorithm improves self-play reinforcement learning for competitive games.

SPIN converts weak LLMs to strong ones using self-play.

The paper develops algorithms for competitive RL in partially observable MGs.

Adversarial self-play in two-player games has delivered impressive results when used with reinforcement learning algorithms that combine deep neural networks and tree search. Algorithms like AlphaZero and Expert Iteration learn tabula-rasa, producing highly informative training data on the fly. However, the self-play t…

New method learns optimal environment and goal difficulty for reinforcement learning.

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 OpenGo and Leela Zero, our bot KataGo only learns from neural-net-guided Monte Carl…

Self-play fine-tuning improves diffusion models for text-to-image generation.

Paper optimizes reinforcement learning in self-play games with reduced steps.

Despite the notable successes in video games such as Atari 2600, current AI is yet to defeat human champions in the domain of real-time strategy (RTS) games. One of the reasons is that an RTS game is a multi-agent game, in which single-agent reinforcement learning methods cannot simply be applied because the environmen…

Study learns optimal strategies in imperfect information games with self-play.

SPPO optimizes language model alignment by treating preferences as a game and achieving state-of-the-art performance.

We introduce a new virtual environment for simulating a card game known as "Big 2". This is a four-player game of imperfect information with a relatively complicated action space (being allowed to play 1,2,3,4 or 5 card combinations from an initial starting hand of 13 cards). As such it poses a challenge for many curre…

OpenAI Five defeated Dota 2 champions using deep reinforcement learning.

This paper proposes using a linear function approximator, rather than a deep neural network (DNN), to bias a Monte Carlo tree search (MCTS) player for general games. This is unlikely to match the potential raw playing strength of DNNs, but has advantages in terms of generality, interpretability and resources (time and …

Many poker systems, whether created with heuristics or machine learning, rely on the probability of winning as a key input. However calculating the precise probability using combinatorics is an intractable problem, so instead we approximate it. Monte Carlo simulation is an effective technique that can be used to approx…

Faster WIND accelerates iterative BOND for LLM alignment.

Algorithm converges to Nash equilibria in competitive games.

Study of geometric analysis on asymmetric metric spaces, including heat flow and Sobolev spaces.

This work improves autonomous racing by creating diverse opponents and adapting risk.

A new algorithm reduces memory and computational needs for reinforcement learning.

New metrics for Anosov representations defined from Thurston's asymmetric metrics.

In recent years, state-of-the-art game-playing agents often involve policies that are trained in self-playing processes where Monte Carlo tree search (MCTS) algorithms and trained policies iteratively improve each other. The strongest results have been obtained when policies are trained to mimic the search behaviour of…

Generalizes Thurston's asymmetric metric to flat metrics.

The problem of retrosynthetic planning can be framed as one player game, in which the chemist (or a computer program) works backwards from a molecular target to simpler starting materials though a series of choices regarding which reactions to perform. This game is challenging as the combinatorial space of possible cho…

This study examines asymmetric cross-correlations in cryptocurrency markets using fractal analysis.

Theoretical justification for asymmetric actor-critic algorithms in reinforcement learning.

This work presents deep asymmetric networks with a set of node-wise variant activation functions. The nodes' sensitivities are affected by activation function selections such that the nodes with smaller indices become increasingly more sensitive. As a result, features learned by the nodes are sorted by the node indices…

We consider the problem of designing locality sensitive hashes (LSH) for inner product similarity, and of the power of asymmetric hashes in this context. Shrivastava and Li argue that there is no symmetric LSH for the problem and propose an asymmetric LSH based on different mappings for query and database points. Howev…

New asymmetric kernel methods improve feature learning.

The article confirms two quasi-alternating surgeries for 9 asymmetric L-space knots.

Asymmetric expansion preserves convexity in hyperbolic geometry.

The paper improves asymmetric causality tests by addressing inefficiencies and statistical significance issues.

We propose Deep Asymmetric Multitask Feature Learning (Deep-AMTFL) which can learn deep representations shared across multiple tasks while effectively preventing negative transfer that may happen in the feature sharing process. Specifically, we introduce an asymmetric autoencoder term that allows reliable predictors fo…

In this paper we show how the study of asymmetric R&D alliances, that are those between young and small firms and large and MNEs firms for knowledge exploration and/or exploitation, requires the adoption of a coopetitive framework which consider both collaboration and competition. We draw upon the literature on asymmet…

High-throughput 3D control training system achieves 100,000 FPS.

A new method for RLHF using proximal point Nash learning.

Bayesian VI copula models capture asymmetric intraday equity dependence.

This work describes compactifications of metric spaces and vector spaces using asymmetric norms.

Building an open-domain conversational agent is a challenging problem. Current evaluation methods, mostly post-hoc judgments of static conversation, do not capture conversation quality in a realistic interactive context. In this paper, we investigate interactive human evaluation and provide evidence for its necessity; …