COCOA improves credit assignment in reinforcement learning by measuring contributions to rewards.
problem Improving sample efficiency in reinforcement learning through better credit assignment methods.
method Counterfactual Contribution Analysis (COCOA) for precise credit assignment.
result COCOA achieves lower bias and variance compared to Hindsight Credit Assignment (HCA), improving reinforcement learning performance.
EgalMAB solves fair resource allocation in stochastic bandits.
problem Fair resource allocation in a stochastic multi-armed bandit setting.
method Design and analysis of UCB-based policy EgalUCB.
result Established upper bounds on cumulative regret.
This paper proposes a new algorithm for learning guidance rewards in RL.
problem Long-term temporal credit assignment in sparse or delayed reward environments.
method Surrogate RL objective with trajectory-space smoothing to learn guidance rewards.
result Guidance rewards can be learned without additional neural networks and have intuitive interpretation.
This paper proposes a definition of system health in the context of multiple agents optimizing a joint reward function. We use this definition as a credit assignment term in a policy gradient algorithm to distinguish the contributions of individual agents to the global reward. The health-informed credit assignment is t…
Transforming sparse outcomes into dense process rewards for efficient reinforcement learning.
problem Training RL policies to maximize sparse outcomes.
method Incentivizing policy matching state-action visitations of successful episodes.
result Significantly faster RL finetuning performance.
Reward shaping is one of the most effective methods to tackle the crucial yet challenging problem of credit assignment in Reinforcement Learning (RL). However, designing shaping functions usually requires much expert knowledge and hand-engineering, and the difficulties are further exacerbated given multiple similar tas…
Improves text-to-image diffusion models using GFlowNets.
problem Aligning diffusion models with text descriptions.
method Post-training diffusion models with GFlowNets to generate high-reward images.
result Effective alignment of large-scale text-to-image diffusion models with reward information.
In this paper, we introduce a novel combined reward cum penalty loss function to handle the regression problem. The proposed combined reward cum penalty loss function penalizes the data points which lie outside the ε-tube of the regressor and also assigns reward for the data points which lie inside of the ε-tube of…
Recent advances in deep reinforcement learning algorithms have shown great potential and success for solving many challenging real-world problems, including Go game and robotic applications. Usually, these algorithms need a carefully designed reward function to guide training in each time step. However, in real world, …
New algorithm balances user reward and statistical inference by mixing TS with UR based on difference size.
problem Combining statistical inference with user reward in adaptive experiments.
method TS-PostDiff algorithm that uses UR when differences are small and TS when large.
result TS-PostDiff reduces false positives and increases statistical power for small differences, while maximizing reward for large ones.
Algorithm solves job acceptance problem with random arrivals and values.
problem Decision-making under random job arrivals and values with limited acceptance.
method Proposes Non-Parametric Sequential Allocation (NPSA) algorithm.
result Expected reward converges to optimality as sample size increases.
In this work, we study the credit assignment problem in reward augmented maximum likelihood (RAML) learning, and establish a theoretical equivalence between the token-level counterpart of RAML and the entropy regularized reinforcement learning. Inspired by the connection, we propose two sequence prediction algorithms, …
This paper explores a simple regularizer for reinforcement learning by proposing Generative Adversarial Self-Imitation Learning (GASIL), which encourages the agent to imitate past good trajectories via generative adversarial imitation learning framework. Instead of directly maximizing rewards, GASIL focuses on reproduc…
Paper introduces OTR for efficient offline RL in surgical robotics.
problem Lack of annotated datasets for offline RL in surgical robotics.
method OTR algorithm using Optimal Transport to assign rewards to unlabeled trajectories.
result OTR enables efficient policy learning from large datasets without handcrafted rewards.
New algorithm minimizes regret in multi-armed bandits with network interference.
problem Minimizing regret in online experiments with network interference.
method Sparse network interference model, discrete Fourier analysis, linear regression-based algorithms.
result Provable low regret algorithms for sparse interference networks.
BERT embeddings improve sequence quality metrics.
problem Measuring the quality of generated sequences against references.
method Employ contextual BERT embeddings for sequence-level reward.
result Contextual embeddings provide a more effective learning signal.
Survive method improves model-based RL by avoiding terminal states, reducing sample complexity.
problem High sample complexity in model-free RL methods limits real-world applications.
method Introduces 'survival' concept to model-based RL, focusing on avoiding terminal states instead of maximizing rewards.
result Survive method reduces training effort by focusing on terminal states, improving model-based RL performance.
PRISM integrates diverse rewards in MORL, improving sample efficiency and Pareto coverage.
problem Heterogeneous MORL where dense objectives dominate, leading to poor sample efficiency.
method PRISM uses reflectional symmetry and ReSymNet to reconcile temporal-frequency mismatches and accelerate exploration.
result PRISM consistently outperforms sparse-reward baselines and oracles, achieving significant Pareto gains.
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.
This paper explores the possibility of near-optimally solving multi-agent, multi-task NP-hard planning problems with time-dependent rewards using a learning-based algorithm. In particular, we consider a class of robot/machine scheduling problems called the multi-robot reward collection problem (MRRC). Such MRRC problem…
The success of popular algorithms for deep reinforcement learning, such as policy-gradients and Q-learning, relies heavily on the availability of an informative reward signal at each timestep of the sequential decision-making process. When rewards are only sparsely available during an episode, or a rewarding feedback i…
Interactive RL and DT feedback improve feature selection efficiency.
problem Balancing feature selection effectiveness and efficiency.
method Interactive Reinforcement Learning (IRL) and Decision Tree Feedback (DTF) architecture.
result Improved feature selection performance on real-world datasets.
New algorithms reduce matching regret by limiting frequent updates.
problem Minimizing regret in stochastic matching with rare optimization updates.
method Batched algorithms that limit matching updates to Θ(log log T) rounds.
result Achieve a regret bound of \(\widetilde{\mathcal{O}}(\sqrt{T})\) with reduced computational cost.
In preference-based reinforcement learning (RL), an agent interacts with the environment while receiving preferences instead of absolute feedback. While there is increasing research activity in preference-based RL, the design of formal frameworks that admit tractable theoretical analysis remains an open challenge. Buil…
New scoring rules improve probabilistic classification model evaluation.
problem Traditional scoring rules misalign with the preference for correct classifications.
method Introduces Penalized Brier Score (PBS) and Penalized Logarithmic Loss (PLL) to modify proper scoring rules.
result PBS and PLL better identify optimal checkpoints and early stopping points, leading to superior F1 scores.
Aims to improve personalized treatment decisions through Bayesian experimental design.
problem Evaluating and improving personalized treatment decisions in contexts like customer service.
method Model-agnostic Bayesian Experimental Design to efficiently gather data and avoid highly sub-optimal treatments.
result Our method achieves superior performance in evaluating and improving treatment decisions compared to traditional approaches.
We investigate a family of regression problems in a semi-supervised setting. The task is to assign real-valued labels to a set of n sample points, provided a small training subset of N labeled points. A goal of semi-supervised learning is to take advantage of the (geometric) structure provided by the large number o…
A new approach for specifying and synthesizing subroutines for optimizing metrics.
problem Specifying and optimizing subroutines for various metrics.
method Formalizing programming by rewards (PBR), using continuous-optimization techniques to synthesize decision functions as if-then-else programs.
result Synthesized decision functions are optimal in cases when rewards have nice properties.
We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. TextWorld is a Python library that handles interactive play-through of text games, as well as backend functions like state tracking and reward assignment. It comes with a curated list of games whose …
This paper investigates the adversarial Bandits with Knapsack (BwK) online learning problem, where a player repeatedly chooses to perform an action, pays the corresponding cost, and receives a reward associated with the action. The player is constrained by the maximum budget B that can be spent to perform actions, an…
Kernel method estimates long-term effects from short-term data.
problem Estimating long-term effects from short-term data in continuous actions.
method Kernel ridge regression to embed and extrapolate long-term effects.
result Uniform consistency and nonasymptotic error bounds for the estimator.
Proposes DISCO, the first CVI for density-based clustering with noise.
problem Evaluation of noise assignments in density-based clustering.
method Density-connectivity and Silhouette Coefficient adaptation for noise evaluation.
result DISCO is the first CVI to explicitly assess noise assignments.
CollaQ improves multi-agent performance in StarCraft by 40% with fewer samples.
problem Limited generalization and high training rounds in multi-agent reinforcement learning.
method Formulates multi-agent collaboration as joint optimization on reward assignment, decomposes Q-function into self and interactive terms, and uses MARA loss.
result Improves win rate by 40% in StarCraft maps with same number of samples compared to state-of-the-art techniques.
Datasets with hundreds to tens of thousands features is the new norm. Feature selection constitutes a central problem in machine learning, where the aim is to derive a representative set of features from which to construct a classification (or prediction) model for a specific task. Our experimental study involves micro…
Paper analyzes online reinforcement learning with outcome-based feedback, providing efficient algorithms and fundamental limits.
problem Assigning credit to actions in reinforcement learning with only endpoint rewards.
method Develops a provably sample-efficient algorithm for online reinforcement learning with general function approximation.
result Achieves O(CmcovH3/ε2) sample complexity, characterizing statistical separation between outcome-based and per-step rewards. A variety of cooperative multi-agent control problems require agents to achieve individual goals while contributing to collective success. This multi-goal multi-agent setting poses difficulties for recent algorithms, which primarily target settings with a single global reward, due to two new challenges: efficient explo…
Open-domain dialog generation is a challenging problem; maximum likelihood training can lead to repetitive outputs, models have difficulty tracking long-term conversational goals, and training on standard movie or online datasets may lead to the generation of inappropriate, biased, or offensive text. Reinforcement Lear…
Sequence generative adversarial networks (SeqGAN) have been used to improve conditional sequence generation tasks, for example, chit-chat dialogue generation. To stabilize the training of SeqGAN, Monte Carlo tree search (MCTS) or reward at every generation step (REGS) is used to evaluate the goodness of a generated sub…
Study examines impact of missing data on multi-armed bandit algorithms.
problem Impact of missing data on performance of multi-armed bandit algorithms.
method Extensive simulation study of two-armed bandit algorithms with binary outcomes, considering different probabilities of missingness.
result Impact on performance varies depending on the balance between exploration and exploitation.
New insights into how to inspect and learn from multi-stage processes and AI reasoning.
problem Understanding how to attribute outcomes to early stages in multi-stage operations and AI reasoning.
method Information-theoretic analysis and mathematical proofs of four key results.
result Uniform checkpoint spacing is minimax-optimal for inspection design under homogeneous signal attenuation.
We propose Stochastic Neural Architecture Search (SNAS), an economical end-to-end solution to Neural Architecture Search (NAS) that trains neural operation parameters and architecture distribution parameters in same round of back-propagation, while maintaining the completeness and differentiability of the NAS pipeline.…
Meta-learning adjusts TD learning's eligibility trace parameter for more efficient reinforcement learning.
problem Efficiently tuning the eligibility trace parameter for temporal difference learning.
method Meta-learning method to adjust eligibility trace parameter state-dependently.
result Improves overall quality of update targets, minimizing target error.
We study a multiplayer stochastic multi-armed bandit problem in which players cannot communicate, and if two or more players pull the same arm, a collision occurs and the involved players receive zero reward. We consider the challenging heterogeneous setting, in which different arms may have different means for differe…
Deep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging control tasks. However, these methods typically suffer from three core difficulties: temporal credit assignment with sparse rewards, lack of effective exploration, and brittle convergence properties that are extremely …
New model tackles interference in online experiments.
problem Understanding cumulative performance in interference experiments.
method Introduces Multi-Armed Bandits with Interference (MABI) model.
result Cluster randomization policy achieves optimal expected regret and high probability bound.
ePF improves PF for ITS by balancing exploration and exploitation, outperforming baselines.
problem Premature exploitation in PF leads to suboptimal solutions under constrained budgets.
method Integrates Entropic Annealing and Look-ahead Modulation to preserve diversity and evaluate potential.
result Significant improvement in task reward (up to 50% relative) on math benchmarks.
Paper extends ranking metrics theory for financial positions.
problem Developing a new class of functionals for evaluating financial positions.
method Axiomatic framework based on monotonicity and cash-quasiconcavity.
result Linking ranking metrics to families of acceptance sets and risk measures.
Paper extends ranking metrics theory for financial positions.
problem Developing a new class of performance evaluation methods.
method Axiomatic framework based on monotonicity and cash-quasiconcavity.
result Linking ranking metrics to families of acceptance sets and risk measures.