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…
On-device research index
arXiv research
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.
168,786 papers · 148 categories
Trend · papers per month
48 results for “joint credit assignment”
LICA learns credit assignment for cooperative agents without explicit formulation.
problem Credit assignment among cooperative agents.
method Centralized critic as hypernetwork, adaptive entropy regularization.
result Significantly outperforms previous methods on benchmarks.
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.
New algorithms assign credit to past decisions based on hindsight.
problem Efficient credit assignment in reinforcement learning.
method Explicit credit assignment using new data in hindsight.
result Value functions can be rewritten to include hindsight credit assignment.
Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysiscs.LG
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.
Who's responsible? Jointly quantifying the contribution of the learning algorithm and training datacs.LG
This work tackles ML accountability by quantifying contributions of algorithms and datasets.
problem Determining responsibility for poor performance on subpopulations at test time.
method Proposes Extended Shapley as a principled framework for joint credit assignment.
result Demonstrates Extended Shapley can be used to address ML accountability questions.
Eigenoptions improve credit assignment in reinforcement learning.
problem Improving credit assignment in reinforcement learning models.
method Investigated eigenoptions for credit assignment in model-free RL, comparing pre-specified and online discovery methods.
result Pre-specified eigenoptions aid exploration and credit assignment, while online discovery can hinder learning.
Credit assignment in Meta-reinforcement learning (Meta-RL) is still poorly understood. Existing methods either neglect credit assignment to pre-adaptation behavior or implement it naively. This leads to poor sample-efficiency during meta-training as well as ineffective task identification strategies. This paper provide…
From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Predictioncs.CL
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, …
The paper formalizes and analyzes multi-agent Q-learning with value factorization.
problem Understanding and improving the convergence of multi-agent Q-learning with value factorization.
method Formalized a multi-agent fitted Q-iteration framework for analyzing factorized multi-agent Q-learning.
result Multi-agent Q-learning with linear value factorization can converge under certain conditions.
A model explains credit assignment in deep learning networks.
problem Understanding how deep learning assigns credit to parameters.
method Mean-field learning model with ensembles of sub-networks.
result Synaptic connections can be categorized into three types.
The paper explores how planning with models improves credit assignment in reinforcement learning.
problem Improving credit assignment in reinforcement learning.
method Investigates the use of forward and backward models for planning in reinforcement learning.
result Establishes the relative merits and limitations of forward and backward planning mechanisms.
Proposes a new model to better handle correlation risk in credit risk calculations.
problem Empirical evidence shows correlation risk is significant in credit risk models.
method Introduces a stochastic correlation extension of the Vasicek model using circular diffusion.
result Demonstrates how correlation volatility and persistence affect joint default and survival probabilities.
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.…
Introduces expected eligibility traces for more efficient credit assignment in reinforcement learning.
problem Efficiently assigning credit to states and actions in reinforcement learning.
method Introduces expected eligibility traces, allowing updates to counterfactual sequences.
result Substantial improvements in temporal-difference learning can be achieved with expected traces.
MRC improves credit assignment in multi-agent LLM systems, achieving high returns and transparency.
problem Lack of principled credit assignment in multi-agent LLM decision systems, vulnerability to regime shifts, and limited transparency.
method Market Regime Council (MRC) computes exact Shapley credits, uses exponentially weighted performance histories, Bayesian adaptive mixture, and regime-dependent multipliers.
result MRC achieves a Sharpe ratio of 1.51 and a cumulative return of 440.1% over 1,037 trading days, ranking first on CR, SR, and IR.
New framework for modular reinforcement learning reduces sample complexity.
problem Achieving independent credit assignment in reinforcement learning.
method Defining modular credit assignment as minimizing algorithmic mutual information, introducing modularity criterion for causal analysis.
result Single-step temporal difference action-value methods meet the modularity criterion, improving sample efficiency.
New methods improve deep reinforcement learning by accelerating credit assignment.
problem Challenges in achieving fast and stable off-policy learning in deep reinforcement learning.
method Extends the generalized PBE objective to support multistep credit assignment and derives three gradient-based methods.
result Proposed methods outperform PPO and StreamQ in MuJoCo and MinAtar environments.
Machine learning improves joint default assessment by capturing non-linear dependencies.
problem Capturing non-linear dependencies among covariates for accurate joint default assessment.
method Application of machine learning techniques to credit card dataset, comparing with logistic regression.
result Machine learning outperforms logistic regression in assessing portfolio riskiness.
Credit risk analysis improved with a joint model for spatial and temporal effects.
problem Predicting borrower's time-to-event with spatial and temporal covariates.
method Spatio-Temporal Joint Model (STJM) using Bayesian hierarchical approach and INLA.
result Spatial effects improve joint model performance, but spatio-temporal interactions have less impact.
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.
The paper introduces ESE scores for farmers to assess climate change risks.
problem Assessing climate change risks in individual farmers' credit evaluations.
method Integrating ESG variables into joint liability models and using a mean-variance utility function.
result Optimal group sizes and individual-ESE score relationships under various climatic conditions.
Proposes a new neural network approach to credit assignment.
problem Credit assignment problem in deep neural networks.
method Contrastive similarity matching objective function.
result Deep networks learn to match similarity between layers.
Shapley Flow interprets model predictions using a graph-based approach to feature importance.
problem Existing feature importance methods ignore or hide feature dependencies.
method Shapley Flow considers the entire causal graph and assigns credit to edges.
result Shapley Flow provides a deeper, graph-based view of feature importance.
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…
Generative Assignment Flows for Representing and Learning Joint Distributions of Discrete Datastat.ML
Generative model for joint discrete distributions using randomized assignment flows.
problem Efficiently representing and sampling from complex joint distributions of discrete variables.
method Randomized assignment flows on the statistical submanifold of factorizing distributions.
result Our model can efficiently represent and sample from any target distribution and assess likelihood of unseen data points.
Paper tackles end-to-end training of complex neural networks using DIP method.
problem Training complex heterogeneous neural network models end-to-end.
method Deep Innovation Protection (DIP) method using multiobjective optimization.
result End-to-end training of complex heterogeneous neural network models is possible.
MACC learns communication protocols by adapting counterfactual reasoning.
problem Credit assignment and non-stationarity in communication environments.
method Adapts counterfactual reasoning to overcome credit assignment and uses action policy and Q-function of other agents to handle non-stationarity.
result MACC outperforms state-of-the-art baselines in four scenarios.
Learning long-term dependencies in extended temporal sequences requires credit assignment to events far back in the past. The most common method for training recurrent neural networks, back-propagation through time (BPTT), requires credit information to be propagated backwards through every single step of the forward c…
A new method reduces variance in training early-stage rankers for large-scale search systems.
problem Training early-stage rankers for large-scale search systems is challenging due to exploding variance in policy gradient methods.
method Proposes credit-assigned policy gradient (CA-PG) to mitigate variance in training early-stage rankers.
result CA-PG significantly reduces variance in training early-stage rankers compared to vanilla policy gradient.
We present a recurrent neural network memory that uses sparse coding to create a combinatoric encoding of sequential inputs. Using several examples, we show that the network can associate distant causes and effects in a discrete stochastic process, predict partially-observable higher-order sequences, and enable a DQN a…
Improved GFlowNets learn more efficiently with trajectory balance.
problem Inefficient credit assignment in GFlowNets leads to suboptimal learning.
method Proposed trajectory balance as a new learning objective.
result Trajectory balance leads to more efficient and robust GFlowNet learning.
Delta-AI speeds up inference in sparse PGMs by local credit assignment.
problem Efficient inference in sparse probabilistic graphical models.
method Local credit assignment in agent's policy learning objective.
result Trained sampler recovers marginals and conditional distributions.
Study improves survival analysis for credit risk by accounting for data drift.
problem Survival analysis in credit risk assumes a stationary data-generating process, but real-world data drift affects model performance.
method Proposes a dynamic joint modelling framework integrating longitudinal behavioural markers and hazard formulations, combined with drift-adaptive techniques.
result Proposed model outperforms classical survival models and drift-adaptive learners in various data drift scenarios.
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…
Small Medium-sized Enterprises (SMEs) face many obstacles when they try to access credit market. These obstacles are increased if the SMEs are innovative. In this case, financial data are insufficient or even not reliable. Thus, when building a judgemental rating model, mainly based on qualitative criteria (soft inform…
Model estimates LIBOR rates and finds COVID-19 spread spike due to credit risk.
problem Estimating LIBOR rates and understanding the factors affecting them.
method Developed a joint model for various LIBOR-related rates and used it to decompose spreads.
result Credit risk mainly caused the spike in LIBOR-OIS spread during the COVID-19 onset, with equal contributions from credit and funding-liquidity risks on average.
Study finds implicit government guarantee improves municipal investment bond ratings.
problem Questioning the objectivity of municipal investment bond ratings due to implicit government guarantee.
method Text mining of policy documents and PMC index model for implicit guarantee strength calculation.
result Implicit government guarantee boosts municipal investment bond ratings, especially in less developed regions.
First passage models, where corporate assets undergo correlated random walks and a company defaults if its assets fall below a threshold provide an attractive framework for modeling the default process. Typical one year default correlations are small, i.e., of order a few percent, but nonetheless including correlations…
The study develops a machine learning system for credit scoring and default prediction.
problem Developing a robust credit rating and default prediction system.
method Combines NLP, AE, GBM, DE, and SHAP/LIME for model interpretability.
result Obtained excellent out-of-sample performance in credit rating and default prediction.
We introduce a dynamic model of the default waterfall of derivatives CCPs and propose a risk sensitive method for sizing the initial margin (IM), and the default fund (DF) and its allocation among clearing members. Using a Markovian structure model of joint credit migrations, our evaluation of DF takes into account the…
Stochastic computation graphs (SCGs) provide a formalism to represent structured optimization problems arising in artificial intelligence, including supervised, unsupervised, and reinforcement learning. Previous work has shown that an unbiased estimator of the gradient of the expected loss of SCGs can be derived from a…
The valuation of counterparty risk for single name credit derivatives requires the computa- tion of joint distributions of default times of two default-prone entities. For a Merton-type model, we derive some formulas for these joint distribu- tions. As an application, closed formulas for counterparty risk on a CDS or f…
Paper proposes a self-learning framework for reject inference in credit scoring.
problem Sample bias in credit scoring models due to training on accepted cases only.
method Develops a self-learning framework considering distinct training regimes for iterative labeling and model training, introduces a new evaluation measure.
result Demonstrates the superiority of the adjusted self-learning framework over regular self-learning and previous reject inference strategies.
Two local learning rules are investigated to avoid weight transport in neural networks.
problem Local learning rules that avoid weight transport are unstable and require tuning.
method Investigated two non-local learning rules and a more robust local rule.
result Non-local learning rules match state-of-the-art performance and operate effectively in noisy updates.
Motivated by the interplay between structural and reduced form credit models, we propose to model the firm value process as a time-changed Brownian motion that may include jumps and stochastic volatility effects, and to study the first passage problem for such processes. We are lead to consider modifying the standard f…
Renewing Reliability: Valuation and Credit Risk Adjustments for Renewable Power Purchase Agreementsq-fin.PR
Paper develops framework for valuing and assessing credit risk in renewable PPAs.
problem Renewable PPAs expose both parties to counterparty credit risk.
method Modelled joint dynamics of electricity prices and renewable output, incorporated default probabilities.
result Provides transparent metric for PPA valuation under counterparty risk.
We study the problem of finding the worst-case joint distribution of a set of risk factors given prescribed multivariate marginals and a nonlinear loss function. We show that when the risk measure is CVaR, and the distributions are discretized, the problem can be conveniently solved using linear programming technique. …