QTRAN factorizes joint action-value function for cooperative MARL without structural constraints.
problem Value-based solutions for multi-agent reinforcement learning with structural constraints.
method QTRAN: transforming joint action-value function into easily factorizable form.
result QTRAN covers a wider class of MARL tasks than previous methods.
QTRAN++ improves MARL performance in complex environments.
problem Poor empirical performance of QTRAN in complex environments.
method Stabilizing training objective, removing role separation, and introducing a multi-head mixing network.
result QTRAN++ achieves state-of-the-art performance in the Starcraft Multi-Agent Challenge (SMAC).
In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting, where global state information is available and communication constraints are lifte…
New approach for open ad hoc teamwork using graph-based policy learning.
problem Designing autonomous agents to collaborate with changing teams without prior coordination.
method Graph-based policy learning to adapt to dynamic team compositions.
result Successfully models the effects of other agents, leading to robust adaptation and superior performance.
QR-MIX models joint state-action values as a distribution to handle randomness in MARL.
problem Randomness in rewards and observations leads to randomness in long-term returns in MARL.
method QR-MIX uses quantile regression and combines it with QMIX and IQN to model joint state-action values as a distribution.
result QR-MIX outperforms QMIX in the StarCraft Multi-Agent Challenge (SMAC) environment.
QMIX combines per-agent values to create decentralised policies.
problem Training decentralised policies from centralised learning.
method QMIX uses a mixing network to estimate joint action-values as a monotonic combination of per-agent values.
result QMIX significantly outperforms existing methods on the StarCraft Multi-Agent Challenge (SMAC).
Transformers learn to predict chess moves with surprising accuracy and strength.
problem Training transformers on chess to predict moves accurately.
method Large-scale chess dataset (10M games), supervised learning with up to 270M parameters.
result Transformers can predict action-values for novel boards with high accuracy.
We propose a flexible method for estimating value functions in reinforcement learning without parametric assumptions.
problem Lack of interpretability in reinforcement learning models, especially in healthcare applications.
method Nonparametric additive model using local kernel regression and basis expansion.
result Personalized, adaptive recommendations for postoperative recovery.
Equivariant CNNs improve RL performance in symmetric environments.
problem Learning equivariant representations for RL in symmetric environments.
method Proposed and studied equivariant CNNs for RL.
result Equivariant CNNs enhance RL performance and sample efficiency.
A new RL algorithm POWR learns world models to estimate action-values.
problem Inaccessibility of explicit action-value functions in RL.
method Learning a world model using conditional mean embeddings and deriving action-value function via matrix operations.
result POWR algorithm converges to global optimum with proven rates.
Q(Δ)-Learning improves Q-Learning by separating action-value functions into different time scales.
problem Q-Learning struggles with bias-variance trade-off, especially in long-term rewards.
method Introduces Q(Δ)-Learning, extending TD(Δ) to decompose Q(Δ)-function into distinct discount factors. result Q(Δ)-Learning achieves better stability and scalability, especially for long-term tasks. We consider the problem of learning the optimal action-value function in the discounted-reward Markov decision processes (MDPs). We prove a new PAC bound on the sample-complexity of model-based value iteration algorithm in the presence of the generative model, which indicates that for an MDP with N state-action pairs a…
RLMM extends psychometric models to larger tasks.
problem Sequential process data from interactive assessments are not well handled by conventional models.
method RLMM decouples person-level choice sensitivity from task-level value representation through a shared parametric action-value function.
result RLMM achieves higher estimation accuracy and lower runtime than MDP-MM in peg-solitaire simulations and AQUALAB gameplay logs.
Improved Q-learning for multi-agent reinforcement learning by weighting joint action values.
problem QMIX restricts Q-values to monotonic mixtures, limiting complex value functions. method Introduced weighted projection to recover optimal policies, improving performance.
result CW QMIX and OW QMIX outperform baseline QMIX on multi-agent tasks.
Extends SW and GSW to compare heterogeneous joint distributions.
problem Limited applicability of SW and GSW to heterogeneous joint distributions.
method Introduces HHRT and PGRT to extend SW and GSW.
result H2SW distance for heterogeneous joint distributions.
Study presents a method to induce a generalized neural network from joint group invariant functions.
problem Encoding rule of neural network internal data representation.
method Systematic method using joint group invariant function on data-parameter domain.
result Induces a generalized neural network and its inverse operator (ridgelet transform).
A new method learns action representations for reinforcement learning.
problem Efficient action-value estimation in reinforcement learning.
method Action hypergraph networks framework for learning action representations.
result Hypergraph Q-networks show effectiveness on various domains.
New research shows exponential lower bounds for planning in MDPs with linearly-realizable optimal action-value functions.
problem Determining the minimum number of queries needed for sound planners in MDPs with linear function approximation.
method Analyzing fixed-horizon and discounted MDPs with a generative model, showing lower bounds on the number of queries required.
result Sound planners need at least exponential number of queries in both fixed-horizon and discounted settings.
New RL algorithm tackles complex discrete action spaces.
problem Challenges in applying on-policy RL in high-dimensional discrete action spaces.
method Action-value critic, correlated actions, gradient sparsification.
result Empirically outperforms related on-policy algorithms.
Improved Q-learning with hindsight factor reduces overestimation errors.
problem Overestimation errors in Q-learning leading to suboptimal policies.
method Introducing a hindsight factor as an additional loss term in Q-learning.
result The hindsight factor significantly reduces overestimation errors and improves stability.
Joint alignment of a collection of functions is the process of independently transforming the functions so that they appear more similar to each other. Typically, such unsupervised alignment algorithms fail when presented with complex data sets arising from multiple modalities or make restrictive assumptions about the …
The paper studies Fourier-Laplace transforms in polynomial OU volatility models for option pricing.
problem Calibrating and pricing options in polynomial Ornstein-Uhlenbeck volatility models.
method Analyzes Fourier-Laplace transforms, connects to Riccati equations, and develops numerical schemes.
result Establishes existence and solution for Riccati equations and provides efficient numerical methods.
Designs new functionals for ranking joint probability distributions based on correlations.
problem Ranking joint probability distributions based on their correlations.
method Using first principles from inference, a set of functionals are designed with the Principle of Constant Correlations (PCC) guiding the construction.
result The n-partite information (NPI) uniquely determines whether inferential transformations preserve, destroy, or create correlations. Off-policy stochastic actor-critic methods rely on approximating the stochastic policy gradient in order to derive an optimal policy. One may also derive the optimal policy by approximating the action-value gradient. The use of action-value gradients is desirable as policy improvement occurs along the direction of stee…
Efficiently combines autoregressive and set-based models for joint distributions.
problem Joint distributions over multiple predictions from set-based models.
method Causal autoregressive buffer that caches context and captures dependencies.
result Up to 20x faster joint sampling and density evaluation, up to 7x lower memory usage.
New method QMLE performs well in complex action spaces without policy gradients.
problem Why policy gradients outperform action-value methods in complex action spaces.
method QMLE framework for action-value methods based on three principles.
result QMLE performs comparably to policy gradient methods in complex action spaces.
Bayesian framework for learning optimal action-value function in MDPs.
problem Uncertainty quantification in MDPs for optimal decision-making strategies.
method Full Bayesian framework including modelling, inference, and decision-making.
result Demonstrates exploration benefits of posterior sampling in MDPs.
New method calculates geometric Brownian motion with affine drift and its integral.
problem Calculating the distribution of geometric Brownian motion with affine drift and its integral.
method Laplace transform approach and Heun differential equation.
result Joint distribution of geometric Brownian motion with affine drift and its integral can be determined.
This paper investigates learning sparse representations and action-value functions simultaneously in deep reinforcement learning.
problem Mitigating catastrophic interference and improving cumulative reward in deep reinforcement learning agents.
method Employing regularization techniques to learn sparse representations and action-value functions incrementally.
result Learning sparse representations can improve performance and robustness in deep reinforcement learning agents.
A new RL paradigm reduces state-action-value function approximation inefficiency.
problem Challenges in state-action-value function approximation for RL.
method State Action Separable Reinforcement Learning (sasRL) decouples action space from value function learning.
result sasRL achieves up to 75% better performance than state-of-the-art MDP-based RL algorithms.
FACMAC combines deep policy gradients with factored critic for multi-agent reinforcement learning.
problem Cooperative multi-agent reinforcement learning in discrete and continuous action spaces.
method FACMAC uses a centralised but factored critic, combining per-agent utilities into a joint action-value function.
result FACMAC outperforms MADDPG and other baselines on multi-agent particle environments and StarCraft II tasks.
Paper presents an efficient exploration method for reinforcement learning.
problem Efficient exploration in reinforcement learning with uncertainty quantification.
method Parameterized Indexed Value Function (PIV) using index sampling.
result Proves the regret bound for learning PIV in a tabular setting and proposes PINs for computational learning.
The paper analyzes multivariate Hawkes processes and their induced population processes.
problem Analyzing the time-dependent joint probability distribution of multivariate Hawkes processes.
method Exact and asymptotic analysis of general multivariate Hawkes processes and their induced population processes.
result Full characterization of the time-dependent joint transform of the multivariate population process and its intensity process.
Paper proposes GAN-DDQN for efficient resource allocation in network slicing.
problem Efficient resource allocation in network slicing with varying service demands.
method Leverage deep reinforcement learning with GAN-DDQN to minimize SSR and SE discrepancies.
result Proposed GAN-DDQN and Dueling GAN-DDQN algorithms improve resource allocation efficiency.
Diffusion-QL uses diffusion models to improve offline RL performance.
problem Offline RL struggles with function approximation errors on out-of-distribution actions.
method Diffusion-QL represents the policy as a conditional diffusion model and optimizes action-values.
result Diffusion-QL achieves state-of-the-art performance on D4RL benchmark tasks.
A critical and challenging problem in reinforcement learning is how to learn the state-action value function from the experience replay buffer and simultaneously keep sample efficiency and faster convergence to a high quality solution. In prior works, transitions are uniformly sampled at random from the replay buffer o…
Unified theorem for deep and shallow joint-equivariant machines.
problem Universal approximation of joint-equivariant machines.
method Constructive universal approximation theorem based on ridgelet transform.
result Unified approximation of deep and shallow networks.
Study improves probabilistic circuits using transformations for better predictions.
problem Predictive limitations of probabilistic circuits in robotic scenarios.
method Integrates transformations into joint probability trees, extending their capabilities.
result Achieves higher likelihoods with fewer parameters on various data sets.
New algorithms speed up inverse reinforcement learning by solving MDPs once.
problem Slow convergence in Maximum Entropy Inverse Reinforcement Learning.
method Deep Inverse Q-learning with constraints exploiting Q-learning.
result Up to several orders of magnitude speedup compared to existing methods.
The paper tackles reward-relevance in offline RL with sparse decision dynamics.
problem Offline reinforcement learning with sparse decision dynamics and estimation sparsity.
method Reward-filtered least-squares policy evaluation using thresholded lasso.
result The method provides theoretical guarantees with sample complexity dependent on sparse component size.
Latent variable models improve RL by facilitating efficient learning and exploration.
problem Improving sample efficiency in reinforcement learning.
method Representation view of latent variable models for state-action value functions, incorporating kernel embeddings and UCB exploration.
result Established sample complexity of the proposed approach in online and offline settings, demonstrated superior performance in benchmarks.
This paper offers a simple method for Bayesian regression with unknown transformations.
problem Joint inference of unknown transformations and model parameters in Bayesian regression is computationally inefficient and cumbersome.
method The paper introduces a Bayesian nonparametric model via the Bayesian bootstrap to directly target the posterior distribution of the transformation.
result The approach delivers joint posterior consistency and efficient Monte Carlo inference for the transformation and all parameters.
New RL method handles large state-action spaces with complex models.
problem Complex models and large state-action spaces in reinforcement learning.
method π-KRVI, an optimistic modification of least-squares value iteration using kernel ridge regression.
result First order-optimal regret guarantees under general settings, improving over state of the art.
I2C enables agents to learn efficient communication without redundancy.
problem Redundant broadcast communication in multi-agent cooperation.
method I2C learns a prior for agent-agent communication via causal inference and reinforcement learning.
result I2C reduces communication overhead and improves multi-agent cooperative performance.
Estimates joint probability distribution from 1-way marginals using low-rank tensors and random projections.
problem Nonparametric estimation of joint probability mass function (PMF) from limited data.
method Low-rank tensor decomposition and random projections to link data to PMF estimation.
result Estimates joint density from 1-way marginals using transformed space and novel algorithm.
This paper explores a new DRL algorithm that approximates both state-value and state-action functions.
problem Overestimation bias in state-action value function.
method Developed and analyzed the Deep Quality-Value (DQV) algorithm to approximate both V and Q functions. result DQV and DQV-Max algorithms perform better due to less overestimation bias in Q function. Deep Reinforcement Learning improves with Weighted Q-Learning to reduce bias and uncertainty.
problem Overestimation and high variance in Q-Learning cause learning algorithms to diverge in complex environments.
method Deep Weighted Q-Learning (Deep WQL) uses Dropout and Monte Carlo sampling to approximate WQL's weights and reduce bias.
result Deep WQL reduces bias and improves performance on benchmarks compared to existing methods.
OPAA estimates probability densities using functional analysis.
problem Estimating probability density functions efficiently and accurately.
method OPAA uses a parallelizable algorithm based on functional analysis to estimate probability distributions.
result OPAA provides an efficient method to estimate probability density functions and normalizing weights.