Search Results for author:
Found 36 papers, 15 papers with code
Llemma: An Open Language Model For Mathematics
We present Llemma, a large language model for mathematics.
Ranked #5 on
Automated Theorem Proving
on miniF2F-test
Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning
It has the additional complexity of requiring decision-making under imperfect information, similar to Texas hold'em poker, which has a significantly smaller game tree (on the order of $10^{164}$ nodes).
Language Models can Solve Computer Tasks
We compare multiple LLMs and find that RCI with the InstructGPT-3+RLHF LLM is state-of-the-art on MiniWoB++, using only a handful of demonstrations per task rather than tens of thousands, and without a task-specific reward function.
Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games
We also introduce an open-source environment for Barrage Stratego, a variant of Stratego with an approximate game tree complexity of $10^{50}$.
XDO: A Double Oracle Algorithm for Extensive-Form Games
NXDO is the first deep RL method that can find an approximate Nash equilibrium in high-dimensional continuous-action sequential games.
Neural Auto-Curricula
When solving two-player zero-sum games, multi-agent reinforcement learning (MARL) algorithms often create populations of agents where, at each iteration, a new agent is discovered as the best response to a mixture over the opponent population.
Neural Auto-Curricula in Two-Player Zero-Sum Games
When solving two-player zero-sum games, multi-agent reinforcement learning (MARL) algorithms often create populations of agents where, at each iteration, a new agent is discovered as the best response to a mixture over the opponent population.
Multi-agent Reinforcement Learning
Vocal Bursts Valence Prediction
Curiosity-Driven Multi-Criteria Hindsight Experience Replay
Dealing with sparse rewards is a longstanding challenge in reinforcement learning.
ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret
DREAM, the only current CFR-based neural method that is model free and therefore scalable to very large games, trains a neural network on an estimated regret target that can have extremely high variance due to an importance sampling term inherited from Monte Carlo CFR (MCCFR).
ASP: Learn a Universal Neural Solver!
Applying machine learning to combinatorial optimization problems has the potential to improve both efficiency and accuracy.
Online Double Oracle
Solving strategic games with huge action space is a critical yet under-explored topic in economics, operations research and artificial intelligence.
AgentKit: Flow Engineering with Graphs, not Coding
The chains of nodes can be designed to explicitly enforce a naturally structured "thought process".
Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks
On a set of 26 benchmark Atari environments, MeanQ outperforms all tested baselines, including the best available baseline, SUNRISE, at 100K interaction steps in 16/26 environments, and by 68% on average.
Solving the Rubik's Cube Without Human Knowledge
A generally intelligent agent must be able to teach itself how to solve problems in complex domains with minimal human supervision.
Confronting Reward Model Overoptimization with Constrained RLHF
Large language models are typically aligned with human preferences by optimizing $\textit{reward models}$ (RMs) fitted to human feedback.
Solving the Rubik's Cube with Approximate Policy Iteration
Autodidactic Iteration is able to learn how to solve the Rubik’s Cube and the 15-puzzle without relying on human data.
Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Coordination
Training policies solely on the team-based reward is often difficult due to its sparsity.
ColosseumRL: A Framework for Multiagent Reinforcement Learning in $N$-Player Games
Much of recent success in multiagent reinforcement learning has been in two-player zero-sum games.
Multiagent Systems
Optimizing Multiagent Cooperation via Policy Evolution and Shared Experiences
Training policies solely on the team-based reward is often difficult due to its sparsity.
Deep machine learning-assisted multiphoton microscopy to reduce light exposure and expedite imaging
The skin dataset includes 550 images for each of the resolution levels.
A* Search Without Expansions: Learning Heuristic Functions with Deep Q-Networks
We use Q* search to solve the Rubik's cube when formulated with a large action space that includes 1872 meta-actions and find that this 157-fold increase in the size of the action space incurs less than a 4-fold increase in computation time and less than a 3-fold increase in number of nodes generated when performing Q* search.
Improving Social Welfare While Preserving Autonomy via a Pareto Mediator
Machine learning algorithms often make decisions on behalf of agents with varied and sometimes conflicting interests.
Independent Natural Policy Gradient Always Converges in Markov Potential Games
Recent results have shown that independent policy gradient converges in MPGs but it was not known whether Independent Natural Policy Gradient converges in MPGs as well.
Temporal-Difference Value Estimation via Uncertainty-Guided Soft Updates
Under the belief that $\beta$ is closely related to the (state dependent) model uncertainty, Entropy Regularized Q-Learning (EQL) further introduces a principled scheduling of $\beta$ by maintaining a collection of the model parameters that characterizes model uncertainty.
Target Entropy Annealing for Discrete Soft Actor-Critic
Soft Actor-Critic (SAC) is considered the state-of-the-art algorithm in continuous action space settings.
Anytime PSRO for Two-Player Zero-Sum Games
PSRO is based on the tabular double oracle (DO) method, an algorithm that is guaranteed to converge to a Nash equilibrium, but may increase exploitability from one iteration to the next.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Self-Play PSRO: Toward Optimal Populations in Two-Player Zero-Sum Games
Instead of adding only deterministic best responses to the opponent's least exploitable population mixture, SP-PSRO also learns an approximately optimal stochastic policy and adds it to the population as well.
Feasible Adversarial Robust Reinforcement Learning for Underspecified Environments
In this paper, we propose Feasible Adversarial Robust RL (FARR), a novel problem formulation and objective for automatically determining the set of environment parameter values over which to be robust.
Illusory Attacks: Detectability Matters in Adversarial Attacks on Sequential Decision-Makers
Autonomous agents deployed in the real world need to be robust against adversarial attacks on sensory inputs.
Game Theoretic Rating in N-player general-sum games with Equilibria
Rating strategies in a game is an important area of research in game theory and artificial intelligence, and can be applied to any real-world competitive or cooperative setting.
Ensemble Value Functions for Efficient Exploration in Multi-Agent Reinforcement Learning
In this work, we propose ensemble value functions for multi-agent exploration (EMAX), a general framework to seamlessly extend value-based MARL algorithms with ensembles of value functions.
Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
To tackle this challenge, we propose GRAD, a novel game-theoretic approach that treats the temporally-coupled robust RL problem as a partially observable two-player zero-sum game.
JiangJun: Mastering Xiangqi by Tackling Non-Transitivity in Two-Player Zero-Sum Games
This paper presents an empirical exploration of non-transitivity in perfect-information games, specifically focusing on Xiangqi, a traditional Chinese board game comparable in game-tree complexity to chess and shogi.
AI Alignment: A Comprehensive Survey
The former aims to make AI systems aligned via alignment training, while the latter aims to gain evidence about the systems' alignment and govern them appropriately to avoid exacerbating misalignment risks.
Scalable Mechanism Design for Multi-Agent Path Finding
In this work, we introduce the problem of scalable mechanism design for MAPF and propose three strategyproof mechanisms, two of which even use approximate MAPF algorithms.
Policy Space Response Oracles: A Survey
In game theory, a game refers to a model of interaction among rational decision-makers or players, making choices with the goal of achieving their individual objectives.
