arXiv research

This study examines deep hedging for S&P 500 options, revealing systematic delta corrections and fragility.

Deep Q-learning agent outperforms traditional hedging in S&P 500 options.

Improved RL policies from offline data with relaxed BC constraints.

Paper tackles offline RL from mixed datasets with adaptive KL regularizer.

This paper proposes a trading strategy using TD3 for stock and cryptocurrency markets.

MVPI framework optimizes risk in reinforcement learning, improving performance in robot simulations.

The paper examines various RL algorithms to address overestimation and noise issues.

In the past few years, off-policy reinforcement learning methods have shown promising results in their application for robot control. Deep Q-learning, however, still suffers from poor data-efficiency and is susceptible to stochasticity in the environment or reward functions which is limiting with regard to real-world a…

When learning behavior, training data is often generated by the learner itself; this can result in unstable training dynamics, and this problem has particularly important applications in safety-sensitive real-world control tasks such as robotics. In this work, we propose a principled and model-agnostic approach to miti…

AlphaGrad optimizes memory usage in RL algorithms by normalizing gradients.

SMEs provide a transparent testbed for RL evaluation.

Paper introduces SALE for better state-action learning in RL.

SAVO actor improves reinforcement learning by avoiding local optima in complex Q-functions.

This paper analyzes DRL strategies in finance, revealing unique trading patterns and performance differences.

Offline RL tackles resource-constrained online deployment with improved policy transfer.

Deep reinforcement learning algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically struggle with achieving effective exploration and are extremely sensitive to the choice of hyperparameters. One reason is that most approaches use a noisy version of their oper…

DRL automates stock market trading with a 2.68 Sharpe Ratio.

Automates RL with sample-efficient hyperparameter optimization.

CARML uses meta-learning to avoid obstacles in 2D vehicle navigation.

FinRL simplifies deep RL for stock trading, making it accessible to beginners.

Bayesian VAR and Elliptical Black-Litterman models improve portfolio optimization during regime changes and heavy-tailed returns.

Deep RL algorithms struggle with noisy rewards in portfolio optimisation.

Research integrates sentiment analysis with reinforcement learning for better trading strategies.

In this paper, a new population-guided parallel learning scheme is proposed to enhance the performance of off-policy reinforcement learning (RL). In the proposed scheme, multiple identical learners with their own value-functions and policies share a common experience replay buffer, and search a good policy in collabora…

Deep neuroevolution and deep reinforcement learning (deep RL) algorithms are two popular approaches to policy search. The former is widely applicable and rather stable, but suffers from low sample efficiency. By contrast, the latter is more sample efficient, but the most sample efficient variants are also rather unstab…

PBCS combines RL and motion planning for better exploration.

Paper introduces a meta-critic for accelerating off-policy actor-critic learning.

Model-based reinforcement learning (MBRL) with model-predictive control or online planning has shown great potential for locomotion control tasks in terms of both sample efficiency and asymptotic performance. Despite their initial successes, the existing planning methods search from candidate sequences randomly generat…

Method models other agents' behaviors without requiring direct observation.

Agent-to-agent finance aims to manage payments and trust for AI agents.

AI agents manage portfolios, improving on human oversight.

New algorithm reduces learning regret in multi-agent systems with unknown dynamics.

RL agents outperform baselines in asset allocation.

TT-DAC-PS: A deterministic actor-critic approach for optimal trade execution

Agents learn to give rewards to others in a shared learning environment.

New algorithm reduces regret in multi-agent bandits with malicious agents.

We formulate and analyze a multi-agent model for the evolution of individual and systemic risk in which the local agents interact with each other through a central agent who, in turn, is influenced by the mean field of the local agents. The central agent is stabilized by a bistable potential, the only stabilizing force…

Algorithm maximizes total reward in multi-agent bandits with adversarial corruptions.

I2C enables agents to learn efficient communication without redundancy.

We present an effective technique for training deep learning agents capable of negotiating on a set of clauses in a contract agreement using a simple communication protocol. We use Multi Agent Reinforcement Learning to train both agents simultaneously as they negotiate with each other in the training environment. We al…

PEAR dynamically reconfigures agent roles to prevent persistent biases in multi-agent debates.

In mix-game which is an extension of minority game, there are two groups of agents; group1 plays the majority game, but the group2 plays the minority game. This paper studies the change of the average winnings of agents and volatilities vs. the change of mixture of agents in mix-game model. It finds that the correlatio…

We propose a method for modeling and learning turn-taking behaviors for accessing a shared resource. We model the individual behavior for each agent in an interaction and then use a multi-agent fusion model to generate a summary over the expected actions of the group to render the model independent of the number of age…

Many learning agents impact a financial market model, showing complex dynamics.

Reinforcement learning (RL) algorithms allow agents to learn skills and strategies to perform complex tasks without detailed instructions or expensive labelled training examples. That is, RL agents can learn, as we learn. Given the importance of learning in our intelligence, RL has been thought to be one of key compone…

Agents collaborate to reduce regret in a multi-agent linear bandit problem with side information.

Adapts agent strategies on-the-fly for better cross-play in cooperative settings.

A novel framework uses goal-conditioned reinforcement learning to generate diverse samples.