Overparameterized models generalize well in offline contextual bandits, but policy-based algorithms struggle.
problem The performance gap between value-based and policy-based algorithms in offline contextual bandits with overparameterized models.
method Analysis of action-stability in objectives and formal proofs of regret bounds.
result The performance gap is due to action-stability of objectives, with value-based objectives being stable and policy-based objectives unstable.
Unified view on selective credit assignment for reinforcement learning.
problem Efficient credit assignment in reinforcement learning.
method Unified temporal-difference algorithms with selective weightings.
result New algorithms for backward credit assignment and off-policy learning.
Value functions struggle to represent transition dynamics, impacting statistical efficiency.
problem Limited representational power of value functions in capturing transition dynamics.
method Case studies of various reinforcement learning problems to explore the limitations of value-based methods.
result Value-based methods can be as efficient as model-based ones in some cases but severely underperform in others due to information loss.
Proposes a value-based method for continuous control without an actor.
problem Computational infeasibility of evaluating Q-values in continuous action spaces.
method Structurally maximizable Q-functions, actor-free approach.
result Performance and sample efficiency comparable to actor-critic methods.
This paper improves reinforcement learning policies in a scalable way.
problem Ensuring monotonic policy improvement in entropy-regularized RL.
method Derives an entropy-aware lower bound and proposes a novel RL algorithm.
result Demonstrates effectiveness in continuous-state tasks using a linear function approximator.
New issue found in value-based reinforcement learning for stochastic environments.
problem Value-based reinforcement learning struggles with stochastic state transitions.
method Demonstrated using a multiobjective Markov Decision Process (MOMDP).
result Approaches may converge to Pareto-dominated solutions instead of optimal ones.
New RL algorithms adapt to time limits, improving task performance.
problem Fixed RL behaviors cannot adapt to different time restrictions.
method Introduced two algorithms for time adaptive RL: Independent Gamma-Ensemble and n-Step Ensemble.
result Zero-shot adaptation between different time restrictions.
New RL algorithm handles delayed feedback with posterior sampling.
problem Challenges of delayed feedback in reinforcement learning with linear function approximation.
method Posterior sampling with delayed feedback for value-based RL.
result Achieves optimal regret guarantee with improved computational efficiency.
Pretraining reinforcement learning methods with demonstrations has been an important concept in the study of reinforcement learning since a large amount of computing power is spent on online simulations with existing reinforcement learning algorithms. Pretraining reinforcement learning remains a significant challenge i…
The paper explores how different loss functions impact reinforcement learning algorithms.
problem Improving reinforcement learning algorithms by optimizing loss functions.
method Comprehensive survey on loss functions in reinforcement learning, proving the benefits of specific loss functions.
result Binary cross-entropy loss leads to first-order bounds and is more efficient than squared loss.
This work explores representation complexity in RL paradigms, revealing model-based RL as the easiest task.
problem Investigating the representation complexity gap among model-based, policy-based, and value-based RL.
method Demonstrated through analysis of Markov decision processes (MDPs) and introduced new classes of MDPs.
result Representation complexity hierarchy: model-based RL > policy-based RL > value-based RL.
Unified framework for CO problems using RL, providing optimal solutions and convergence guarantees.
problem Combinatorial optimization problems
method Unified framework of Markov decision processes (MDPs) and value-based reinforcement learning (RL) techniques
result RL techniques converge to approximate solutions with a guarantee on optimality gap
The basic financial purpose of a firm is to maximize its value. An inventory management system should also contribute to realization of this basic aim. Many current asset management models currently found in financial management literature were constructed with the assumption of book profit maximization as basic aim. H…
New method improves off-policy critic evaluation in reinforcement learning.
problem High variance and instability in off-policy policy evaluation.
method Doubly robust estimators applied to actor-critic algorithms.
result Doubly robust estimation significantly improves performance in continuous control tasks.
New findings show good representations alone are insufficient for efficient reinforcement learning.
problem Understanding when good representations are enough for efficient reinforcement learning.
method Statistical analysis of reinforcement learning methods, focusing on value-based, model-based, and policy-based learning.
result Hard thresholds for reinforcement learning methods show good representations alone are insufficient, unless they meet certain quality criteria.
A new multi-agent learning method improves performance in complex games.
problem Performance gap between MAPG and value-based multi-agent approaches.
method Introduces value function decomposition into multi-agent actor-critic framework for off-policy learning.
result DOP significantly outperforms state-of-the-art multi-agent reinforcement learning algorithms.
This paper analyzes the sample complexity of two timescale reinforcement learning algorithms.
problem Analyzing the sample complexity of two timescale reinforcement learning algorithms.
method Non-asymptotic analysis of linear and nonlinear TDC and Greedy-GQ algorithms under Markovian sampling with constant stepsize.
result The paper provides non-asymptotic convergence results for two timescale linear and nonlinear TDC and Greedy-GQ algorithms.
TF-Coder simplifies tensor manipulation programming in TensorFlow.
problem Difficulty in programming with TensorFlow due to steep learning curve.
method Bottom-up weighted enumerative search with value-based pruning and type/value filtering.
result Solves 63 out of 70 real-world tasks within 5 minutes.
This paper aims at theoretically and empirically comparing two standard optimization criteria for Reinforcement Learning: i) maximization of the mean value and ii) minimization of the Bellman residual. For that purpose, we place ourselves in the framework of policy search algorithms, that are usually designed to maximi…
Distributional approaches to value-based reinforcement learning model the entire distribution of returns, rather than just their expected values, and have recently been shown to yield state-of-the-art empirical performance. This was demonstrated by the recently proposed C51 algorithm, based on categorical distributiona…
Study evaluates valuation models for UK companies using case studies.
problem Determining how accounting numbers affect business value.
method Comprehensive review of three valuation models: FCFVM, REVM, AEGM.
result Accounting numbers through valuation models can affect business value.
Tutorial on optimizing diffusion model samples for specific metrics.
problem Optimizing diffusion model samples for specific downstream metrics.
method Review and exploration of inference-time guidance and alignment methods.
result Unified perspective on inference-time algorithms and novel methods.
Paper proposes exploiting Q function structures for better planning and RL.
problem Value-based methods in planning and RL.
method Exploiting low-rank structure of Q function using Matrix Estimation techniques.
result Improved planning and RL performance on 'low-rank' tasks.
Stochastic Q-learning tackles large action spaces with reduced computation.
problem Effective decision-making in complex environments with large discrete action spaces.
method Stochastic value-based RL approaches that consider a sublinear number of actions in each iteration.
result Stochastic Q-learning achieves near-optimal returns with significantly reduced computation time.
In this paper we present a novel quasi-Newton algorithm for use in stochastic optimisation. Quasi-Newton methods have had an enormous impact on deterministic optimisation problems because they afford rapid convergence and computationally attractive algorithms. In essence, this is achieved by learning the second-order (…
Most learning algorithms are not invariant to the scale of the function that is being approximated. We propose to adaptively normalize the targets used in learning. This is useful in value-based reinforcement learning, where the magnitude of appropriate value approximations can change over time when we update the polic…
Reincarnating RL reuses prior work to accelerate RL progress.
problem Efficiency and accessibility in reinforcement learning for large-scale applications.
method Transfer of learned policies between RL agents or design iterations, focusing on value-based RL.
result Demonstrated gains in performance over tabula rasa RL on various tasks.
The goal of imitation learning is for an apprentice to learn how to behave in a stochastic environment by observing a mentor demonstrating the correct behavior. Accurate prior knowledge about the correct behavior can reduce the need for demonstrations from the mentor. We present a novel approach to encoding prior knowl…
Paper optimizes traffic signal control for better traffic flow.
problem Optimizing traffic signal control to reduce congestion and improve safety.
method Value-based reinforcement learning with interpretable policy functions (polynomial functions).
result Deep Regulatable Hardmax Q-learning variant reduces vehicle delay by up to 19.4%.
Paper proposes using tree-based surrogate models for efficient Shapley computation.
problem Efficient computation of Shapley values using conditional expectations.
method Surrogate model-based tree for approximating Shapley and SHAP values.
result The proposed algorithm improves accuracy and unifies global interpretation.
In this work, we consider the problem of model selection for deep reinforcement learning (RL) in real-world environments. Typically, the performance of deep RL algorithms is evaluated via on-policy interactions with the target environment. However, comparing models in a real-world environment for the purposes of early …
We analyze reinforcement learning algorithms using a distributional approach.
problem Theoretical analysis of reinforcement learning algorithms for constant step-sizes.
method Distributional approach to theoretical analyses of reinforcement learning algorithms.
result TD( λ λ λ ) and Q Q Q -Learning have contractive update rules in the space of distributions of functions, leading to exponentially fast convergence. The paper studies uncertainty quantification and exploration in RL, providing methods and results.
problem Fundamental questions about inference and error quantification in RL remain open.
method The paper fills the literature gap by studying central limit theorem behaviors of Q-values and value functions.
result Explicitly identified closed-form expressions of asymptotic variances for Q-values and value functions.
In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies. We show that this problem persists in an actor-critic setting and propose novel mechanisms to minimize its effects on both the actor and the cr…
Unified framework for finite-sample RL algorithms using Lyapunov theory.
problem Finite-sample convergence guarantees of asynchronous RL algorithms.
method Reformulate RL algorithms as Markovian SA, develop Lyapunov analysis.
result Mean-square error bounds and convergence for various RL algorithms.
New methods estimate transport-growth pairs in unbalanced optimal transport.
problem Statistical guarantees for Monge-type estimation in unbalanced optimal transport remain limited.
method Developed two estimators for transport-growth pairs under different setups.
result Achieved minimax optimal rate for estimation of transport-growth pairs.
MAVEN improves multi-agent exploration by hybridizing value and policy-based methods.
problem Exploration and suboptimality in complex multi-agent environments.
method MAVEN combines value and policy-based approaches with a latent space for hierarchical control.
result MAVEN achieves significant performance improvements on challenging multi-agent tasks.
OPPO optimizes policy learning with provable efficiency.
problem Designing efficient policy optimization algorithms that incorporate exploration.
method Proposes an Optimistic Proximal Policy Optimization (OPPO) algorithm.
result Achieves i l d e O ( d 2 H 3 T ) ilde{O}(\sqrt{d^2 H^3 T} ) i l d e O ( d 2 H 3 T ) regret in episodic MDPs. Valid p-value for bounded random variables without distributional assumptions.
problem Calibration of predictive algorithms in a distribution-free setting.
method Built a super-uniform p-value based on a concentration inequality.
result Super-uniform p-value is tighter than existing alternatives.
Privileged Information Dropout improves RL performance without distillation.
problem Improving sample efficiency and performance in reinforcement learning.
method Introducing Privileged Information Dropout to directly incorporate privileged information into RL agent inputs.
result Privileged Information Dropout outperforms distillation and auxiliary tasks in a partially-observed environment.
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…
Novel algorithm identifies nonlinear Granger causal relationships using kernel ridge regression.
problem Identification of nonlinear Granger causal relationships.
method Flexible plug-in architecture with kernel ridge regression using radial basis function.
result Kernel ridge regression in mlcausality achieves competitive AUC scores and more finely calibrated p-values.
Paper analyzes Greedy-GQ for reinforcement learning with Markovian noise.
problem Analyzing Greedy-GQ for reinforcement learning with Markovian noise.
method Develops finite-sample analysis for Greedy-GQ with linear function approximation under Markovian noise.
result Provides theoretical justification for choosing stepsizes for faster convergence.
Paper presents a GMFG framework for large stochastic games.
problem Learning Nash Equilibrium in large stochastic games.
method Value-based and policy-based reinforcement learning algorithms with smoothed policies.
result Proposed algorithms GMF-V and GMF-P are efficient and robust in GMFG setting.
Unified analysis of stochastic iterative algorithms using Lyapunov functions.
problem Analyzing convergence of stochastic iterative algorithms for fixed-point equations.
method Lyapunov-based techniques for finite-time analysis of stochastic approximation algorithms.
result Unified mean-square convergence guarantees for various algorithms.
A new method uses Shapley values to select important features for classification.
problem Feature selection for improving classification models.
method Classification game with Shapley value apportioning of hinge loss.
result Threshold 0 on SVEA value identifies significant features.
Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Currently, deep learning is enabling reinforcement learning to scale to problems that were previously intractable, such as learning to p…
A scalable MARL algorithm using local rewards for cooperative multi-agent learning.
problem Scalability issues in cooperative multi-agent reinforcement learning due to large state and action spaces.
method LOMAQ algorithm incorporating local rewards in centralized training and decentralized execution.
result LOMAQ scales well compared to other methods, improving performance and convergence speed.