arXiv research

This work formalizes and extends parameter sharing in multi-agent reinforcement learning.

Developed policy gradient methods for stochastic control with exit time, outperforming traditional techniques in share repurchase pricing.

PPG separates policy and value function training phases for better reinforcement learning efficiency.

Optimal vehicle repositioning policy found for shared mobility services.

Most deep reinforcement learning algorithms are data inefficient in complex and rich environments, limiting their applicability to many scenarios. One direction for improving data efficiency is multitask learning with shared neural network parameters, where efficiency may be improved through transfer across related tas…

Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network parameters, which performs multiple tasks concurrently. However such compound polic…

Deep RL policies share adversarial features across different MDPs.

New estimator uses clustering to improve off-policy evaluation accuracy.

ABPS improves RL training efficiency by sharing policies and evolving hyper-params.

Meta-RL learns shared and task-specific information for quick adaptation.

RL agents fail to generalize to unseen environments, even when dynamics are similar.

Efficient actor-critic learning with shared experience replay improves data efficiency.

PFedRL-Rep learns shared and personalized policies for heterogeneous environments.

Variable renewables can avoid market value decline with policy changes.

SHHK Stock Connect increases A-H share price premium, more for less efficient markets.

We consider the problem of dynamic buying and selling of shares from a collection of $N$ stocks with random price fluctuations. To limit investment risk, we place an upper bound on the total number of shares kept at any time. Assuming that prices evolve according to an ergodic process with a mild decaying memory proper…

BASIS improves LLM reasoning by sharing batchwise rollout info, reducing MSE by 69%.

ICIL learns policies invariant to multiple environments, improving generalization.

Unified policy controls diverse agents through modular neural networks.

This paper improves auto-augment efficiency by sharing augmentation weights.

This paper analyzes the quantitative relations between stock prices and quantities of tradable stock shares in Chinese stock markets at six time points by means of Exploratory Data Analysis (EDA) method. It is found the resulting formulae have the same structure but different parameters. This paper also uses these rela…

The paper introduces return parity for fairness in MDPs, addressing delayed and adverse effects.

Learning policies that generalize across multiple tasks is an important and challenging research topic in reinforcement learning and robotics. Training individual policies for every single potential task is often impractical, especially for continuous task variations, requiring more principled approaches to share and t…

FLAP adapts policies quickly to new tasks using shared linear representations.

A new framework uses multi-agent reinforcement learning for evaluating policies in two-sided markets.

Soft modularization improves sample efficiency and performance in reinforcement learning.

In this paper, we propose a distributed off-policy actor critic method to solve multi-agent reinforcement learning problems. Specifically, we assume that all agents keep local estimates of the global optimal policy parameter and update their local value function estimates independently. Then, we introduce an additional…

Improved SAC with AWMP for better control tasks.

Multi-agent reinforcement learning systems aim to provide interacting agents with the ability to collaboratively learn and adapt to the behaviour of other agents. In many real-world applications, the agents can only acquire a partial view of the world. Here we consider a setting whereby most agents' observations are al…

This paper studies the deviations of the regret in a stochastic multi-armed bandit problem. When the total number of plays n is known beforehand by the agent, Audibert et al. (2009) exhibit a policy such that with probability at least 1-1/n, the regret of the policy is of order log(n). They have also shown that such a …

Generative neural nets learn deep policies conditioned on goals.

RHPO improves data-efficiency for hierarchical reinforcement learning.

We introduce reinforcement learning for heterogeneous teams in which rewards for an agent are additively factored into local costs, stimuli unique to each agent, and global rewards, those shared by all agents in the domain. Motivating domains include coordination of varied robotic platforms, which incur different costs…

We present POLO --- a C++ library for large-scale parallel optimization research that emphasizes ease-of-use, flexibility and efficiency in algorithm design. It uses multiple inheritance and template programming to decompose algorithms into essential policies and facilitate code reuse. With its clear separation between…

Accelerates policy optimization in RL with optimistic and adaptive updates.

Multiagent reinforcement learning algorithms (MARL) have been demonstrated on complex tasks that require the coordination of a team of multiple agents to complete. Existing works have focused on sharing information between agents via centralized critics to stabilize learning or through communication to increase perform…

This work ensures policy gradient methods converge to global optima for certain control problems.

We present Multitask Soft Option Learning(MSOL), a hierarchical multitask framework based on Planning as Inference. MSOL extends the concept of options, using separate variational posteriors for each task, regularized by a shared prior. This ''soft'' version of options avoids several instabilities during training in a …

A mechanism to share risks and costs with guarantees against extreme outcomes.

The paper tackles robust policy learning in multitask contextual bandits with adversarial users.

Safe-M$^3$-UCRL learns safe policies for multi-agent systems with global constraints.

Enhances RL performance with a population-guided parallel learning scheme.

Paper tackles multi-view reinforcement learning with two methods.

Paper tackles robust decision-making from multiple sites with shared structure.

Optimizes insurance pricing by accounting for policyholders' price sensitivity.

Many currently deployed Reinforcement Learning agents work in an environment shared with humans, be them co-workers, users or clients. It is desirable that these agents adjust to people's preferences, learn faster thanks to their help, and act safely around them. We argue that most current approaches that learn from hu…

Study multi-agent RL in OTC markets, learning from agents' interactions.

Investigates optimal pension policies in PAYG systems with forward utility and ageing population.