arXiv research

New RL approach learns dynamic VCG mechanisms in unknown MDP environments.

Improved selection of best outputs from LLMs for better accuracy.

New findings on universal learning in contextual bandits with adversarial rewards.

A new algorithm balances exploration and exploitation in online decision-making.

New acquisition function for extreme rewards in bandits.

New method for contextual bandit with missing rewards.

We propose a generic, Bayesian, information geometric approach to the exploration--exploitation trade-off in multi-armed bandit problems. Our approach, BelMan, uniformly supports pure exploration, exploration--exploitation, and two-phase bandit problems. The knowledge on bandit arms and their reward distributions is su…

Proposes a new RL method to fine-tune flow-based models with arbitrary rewards.

Algorithm learns optimal coordination for strategic agents in uncertain settings.

New method makes reinforcement learning robust to heavy-tailed rewards.

Algorithm learns optimal dynamic mechanisms from data.

A key impediment to reinforcement learning (RL) in real applications with limited, batch data is defining a reward function that reflects what we implicitly know about reasonable behaviour for a task and allows for robust off-policy evaluation. In this work, we develop a method to identify an admissible set of reward f…

Study explores strategies for randomized allocation in delayed rewards bandits.

Meta-learning curiosity algorithms improves exploration across various tasks.

Deep reinforcement learning has obtained significant breakthroughs in recent years. Most methods in deep-RL achieve good results via the maximization of the reward signal provided by the environment, typically in the form of discounted cumulative returns. Such reward signals represent the immediate feedback of a partic…

TLRS improves predictive power of mined formulaic alpha factors.

LNUCB-TA improves MAB performance by dynamically adjusting exploration rates and recognizing spatiotemporal patterns.

Some online advertising offers pay only when an ad elicits a response. Randomness and uncertainty about response rates make showing those ads a risky investment for online publishers. Like financial investors, publishers can use portfolio allocation over multiple advertising offers to pursue revenue while controlling r…

Reinforcement learning in multi-agent scenarios is important for real-world applications but presents challenges beyond those seen in single-agent settings. We present an actor-critic algorithm that trains decentralized policies in multi-agent settings, using centrally computed critics that share an attention mechanism…

Novel RL approach for molecular design using quantum mechanics.

Off-policy evaluation for MNAR rewards in MDPs

Contextual bandits are online learners that, given an input, select an arm and receive a reward for that arm. They use the reward as a learning signal and aim to maximize the total reward over the inputs. Contextual bandits are commonly used to solve recommendation or ranking problems. This paper considers a learning s…

The paper explores a Multi-Objective RL approach for trading that generalizes reward functions.

Binary determination of the presence of objects is one of the problems where humans perform extraordinarily better than computer vision systems, in terms of both speed and preciseness. One of the possible reasons is that humans can skip most of the clutter and attend only on salient regions. Recurrent attention models …

Method uses ANN to estimate incentive salience from large behavioral data.

Recently, GAIL framework and various variants have shown remarkable possibilities for solving practical MDP problems. However, detailed researches of low-level, and high-dimensional state input in this framework, such as image sequences, has not been conducted. Furthermore, the cost function learned in the traditional …

Learning about many things can provide numerous benefits to a reinforcement learning system. For example, learning many auxiliary value functions, in addition to optimizing the environmental reward, appears to improve both exploration and representation learning. The question we tackle in this paper is how to sculpt th…

In reinforcement learning, a decision needs to be made at some point as to whether it is worthwhile to carry on with the learning process or to terminate it. In many such situations, stochastic elements are often present which govern the occurrence of rewards, with the sequential occurrences of positive rewards randoml…

CARDS improves decoding efficiency and alignment quality for LLMs.

Transfer learning across different reinforcement learning (RL) tasks is becoming an increasingly valuable area of research. We consider a goal-based multi-task RL framework and mechanisms by which previously solved tasks can reduce sample complexity and regret when the agent is faced with a new task. Specifically, we i…

Unified framework for human-like decision making in various sequential tasks.

This paper tackles distribution shift in model-based offline RL, proposing a shifts-aware reward method.

Motivated by problems in search and detection we present a solution to a Combinatorial Multi-Armed Bandit (CMAB) problem with both heavy-tailed reward distributions and a new class of feedback, filtered semibandit feedback. In a CMAB problem an agent pulls a combination of arms from a set $\{1,...,k\}$ in each round, g…

A new method boosts exploration in bandit algorithms, reducing regret.

A novel approach for safe offline RL using latent safety constraints.

Study adapts combinatorial semi-bandit for piecewise stationary, causally related rewards.

We propose a unified mechanism for achieving coordination and communication in Multi-Agent Reinforcement Learning (MARL), through rewarding agents for having causal influence over other agents' actions. Causal influence is assessed using counterfactual reasoning. At each timestep, an agent simulates alternate actions t…

Backtesting framework for CLMMs on Uniswap V3 reduces reward estimation error.

ESPD improves learning efficiency in sparse reward reinforcement learning.

Study on private and robust multi-armed bandits with contaminated heavy-tailed rewards.

A novel incentive mechanism improves fairness and participation in federated learning.

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…

Proposes method to discover diverse near-optimal policies in reinforcement learning.

In this paper we explore methods to exploit symmetries for ensuring sample efficiency in reinforcement learning (RL), this problem deserves ever increasing attention with the recent advances in the use of deep networks for complex RL tasks which require large amount of training data. We introduce a novel method to dete…

In light of the growing interest in agent-based market models, we bring together several earlier works in which we considered the topic of self-consistent market modelling. Building upon the binary game structure of Challet and Zhang, we discuss generalizations of the strategy reward scheme such that the agents seek to…

A new algorithm improves stochastic linear bandit performance using residual bootstrap.

This paper explores how environmental properties can simplify reinforcement learning in non-episodic settings.

New method prevents RLHF alignment collapse by accounting for policy's influence on reward model updates.