A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Simple model-based reinforcement learning outperforms model-free methods in complex tasks.
Paper proves efficiency of MARL with transformers, addressing agent complexity.
Enhances RL agents with predictive internal representations.
Efficient exploration for automatic subgoal discovery is a challenging problem in Hierarchical Reinforcement Learning (HRL). In this paper, we show that intrinsic motivation learning increases the efficiency of exploration, leading to successful subgoal discovery. We introduce a model-free subgoal discovery method base…
Agents learn social skills from each other, improving performance.
The field of reinforcement learning (RL) is facing increasingly challenging domains with combinatorial complexity. For an RL agent to address these challenges, it is essential that it can plan effectively. Prior work has typically utilized an explicit model of the environment, combined with a specific planning algorith…
Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents. Here we explore whether causal reasoning can emerge via meta-reinforcement learning. We train a recurrent network with model-free reinforcement learning to solve a range of problems that each contain causal…
RL agents outperform baselines in asset allocation.
Dynamic portfolio optimization is the process of sequentially allocating wealth to a collection of assets in some consecutive trading periods, based on investors' return-risk profile. Automating this process with machine learning remains a challenging problem. Here, we design a deep reinforcement learning (RL) architec…
When agents interact with a complex environment, they must form and maintain beliefs about the relevant aspects of that environment. We propose a way to efficiently train expressive generative models in complex environments. We show that a predictive algorithm with an expressive generative model can form stable belief-…
Simple object representations improve model-free RL performance.
Federated Q-Learning achieves linear regret speedup with low communication cost.
Paper develops efficient algorithms for zero-sum Markov games with general function classes.
In this thesis, we develop a comprehensive account of the expressive power, modelling efficiency, and performance advantages of so-called trading agents (i.e., Deep Soft Recurrent Q-Network (DSRQN) and Mixture of Score Machines (MSM)), based on both traditional system identification (model-based approach) as well as on…
We introduce "Search with Amortized Value Estimates" (SAVE), an approach for combining model-free Q-learning with model-based Monte-Carlo Tree Search (MCTS). In SAVE, a learned prior over state-action values is used to guide MCTS, which estimates an improved set of state-action values. The new Q-estimates are then used…
New RL algorithms reduce costs for single-agent and federated learning.
Agents need world models to generalize multi-step tasks.
New algorithm tackles non-stationary RL with near-optimal regret bounds.
PPOPT uses pretraining to speed up reinforcement learning in physics simulations.
How to best explore in domains with sparse, delayed, and deceptive rewards is an important open problem for reinforcement learning (RL). This paper considers one such domain, the recently-proposed multi-agent benchmark of Pommerman. This domain is very challenging for RL --- past work has shown that model-free RL algor…
Learning by experience in Multi-Agent Systems (MAS) is a difficult and exciting task, due to the lack of stationarity of the environment, whose dynamics evolves as the population learns. In order to design scalable algorithms for systems with a large population of interacting agents (e.g. swarms), this paper focuses on…
Model-free reinforcement learning (RL) can be used to learn effective policies for complex tasks, such as Atari games, even from image observations. However, this typically requires very large amounts of interaction -- substantially more, in fact, than a human would need to learn the same games. How can people learn so…
Improves sample efficiency in RL by matching model-based gradients.
PackIt creates a virtual space for testing geometric planning skills.
Policy-gradient method controls multiple non-cohesive targets.
Improved model-based reinforcement learning for multi-agent Markov games.
DREAM learns optimal strategies in imperfect games without needing a simulator.
New algorithm improves sample efficiency for zero-sum Markov games.
Model-based reinforcement learning methods typically learn models for high-dimensional state spaces by aiming to reconstruct and predict the original observations. However, drawing inspiration from model-free reinforcement learning, we propose learning a latent dynamics model directly from rewards. In this work, we int…
Paper proposes FedQ-Advantage for federated Q-learning with near-optimal regret and low communication cost.
We develop model free PAC performance guarantees for multiple concurrent MDPs, extending recent works where a single learner interacts with multiple non-interacting agents in a noise free environment. Our framework allows noisy and resource limited communication between agents, and develops novel PAC guarantees in this…
Improved model-based reinforcement learning for interactive dialogue tasks reduces sample needs and improves performance.
We introduce Imagination-Augmented Agents (I2As), a novel architecture for deep reinforcement learning combining model-free and model-based aspects. In contrast to most existing model-based reinforcement learning and planning methods, which prescribe how a model should be used to arrive at a policy, I2As learn to inter…
Framework uses probabilistic programming for physics simulation in games.
Quantitative finance has had a long tradition of a bottom-up approach to complex systems inference via multi-agent systems (MAS). These statistical tools are based on modelling agents trading via a centralised order book, in order to emulate complex and diverse market phenomena. These past financial models have all rel…
In this paper, we propose a reinforcement learning-based algorithm for trajectory optimization for constrained dynamical systems. This problem is motivated by the fact that for most robotic systems, the dynamics may not always be known. Generating smooth, dynamically feasible trajectories could be difficult for such sy…
Reinforcement Learning (RL) agents require the specification of a reward signal for learning behaviours. However, introduction of corrupt or stochastic rewards can yield high variance in learning. Such corruption may be a direct result of goal misspecification, randomness in the reward signal, or correlation of the rew…
We consider model-based reinforcement learning (MBRL) in 2-agent, high-fidelity continuous control problems -- an important domain for robots interacting with other agents in the same workspace. For non-trivial dynamical systems, MBRL typically suffers from accumulating errors. Several recent studies have addressed thi…
Training an agent to solve control tasks directly from high-dimensional images with model-free reinforcement learning (RL) has proven difficult. A promising approach is to learn a latent representation together with the control policy. However, fitting a high-capacity encoder using a scarce reward signal is sample inef…
Collective motion of animal groups often undergoes changes due to perturbations. In a topological sense, we describe these changes as switching between low-dimensional embedding manifolds underlying a group of evolving agents. To characterize such manifolds, first we introduce a simple mapping of agents between time-st…
In the past, financial stock markets have been studied with previous generations of multi-agent systems (MAS) that relied on zero-intelligence agents, and often the necessity to implement so-called noise traders to sub-optimally emulate price formation processes. However recent advances in the fields of neuroscience an…
The goal of reinforcement learning (RL) is to let an agent learn an optimal control policy in an unknown environment so that future expected rewards are maximized. The model-free RL approach directly learns the policy based on data samples. Although using many samples tends to improve the accuracy of policy learning, c…
A major component of overfitting in model-free reinforcement learning (RL) involves the case where the agent may mistakenly correlate reward with certain spurious features from the observations generated by the Markov Decision Process (MDP). We provide a general framework for analyzing this scenario, which we use to de…
New method uses LP to achieve optimal sample complexity in multi-agent reinforcement learning.
RL optimizes meta-order execution by adapting to market conditions.
Combines model-based and model-free RL for better financial market performance.
Paper tackles delays in multi-agent reinforcement learning, improving performance.
RL agents optimize order execution in a realistic market simulation.