We consider the problem of off-policy evaluation in Markov decision processes. Off-policy evaluation is the task of evaluating the expected return of one policy with data generated by a different, behavior policy. Importance sampling is a technique for off-policy evaluation that re-weights off-policy returns to account…
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “behavior policies”
The paper explains why estimating a history-dependent policy can reduce MSE in reinforcement learning.
problem Understanding why history-dependent policies can improve MSE in off-policy evaluation.
method The paper derives a bias-variance decomposition of MSE for various OPE estimators, showing how history-dependent policies can decrease variance and increase bias.
result History-dependent policies can decrease the variance of importance sampling estimators, leading to lower MSE.
We introduce a new approach for comparing reinforcement learning policies, using Wasserstein distances (WDs) in a newly defined latent behavioral space. We show that by utilizing the dual formulation of the WD, we can learn score functions over policy behaviors that can in turn be used to lead policy optimization towar…
Study minimax off-policy evaluation in multi-armed bandits with known and unknown behavior policies.
problem Evaluate policies in multi-armed bandits with unknown behavior policies.
method Develop minimax rate-optimal procedures for known and unknown behavior policies, including the Switch estimator and Chebyshev polynomial-based estimator.
result Plug-in estimator achieves optimal competitive ratio up to a logarithmic factor when behavior policy is unknown.
We propose a novel approach to train a multi-modal policy from mixed demonstrations without their behavior labels. We develop a method to discover the latent factors of variation in the demonstrations. Specifically, our method is based on the variational autoencoder with a categorical latent variable. The encoder infer…
We make policy optimization algorithms batch size-invariant by decoupling proximal and behavior policies.
problem Some policy optimization algorithms do not have batch size-invariance, leading to inefficiencies.
method We decouple the proximal policy from the behavior policy to achieve batch size-invariance.
result Our approach makes policy optimization algorithms more efficient and allows them to use stale data more effectively.
AIPS improves ranking policy evaluation by adapting to diverse user behavior.
problem Inaccurate Off-Policy Evaluation of ranking policies due to high variance under diverse user behavior.
method Developed Adaptive IPS (AIPS) that adapts to different user behaviors and minimizes MSE.
result AIPS achieves minimum variance among unbiased estimators and provides significant empirical accuracy improvement.
CoinDICE estimates confidence intervals for unknown behavior policies in reinforcement learning.
problem Estimating value of a target policy using only behavior policy data.
method Function space embedding, generalized empirical likelihood method, Lagrangian optimization.
result Valid confidence intervals with tighter and more accurate estimates than existing methods.
Off-policy learning exhibits greater instability when compared to on-policy learning in reinforcement learning (RL). The difference in probability distribution between the target policy () and the behavior policy (b) is a major cause of instability. High variance also originates from distributional mismatch. The var…
Learning algorithms are enabling robots to solve increasingly challenging real-world tasks. These approaches often rely on demonstrations and reproduce the behavior shown. Unexpected changes in the environment may require using different behaviors to achieve the same effect, for instance to reach and grasp an object in…
FOCOPS optimizes agent's behavior while adhering to constraints.
problem Optimizing agent's behavior while respecting safety constraints.
method FOCOPS solves a constrained optimization problem in policy space, then projects the solution back into the parametric space.
result FOCOPS achieves better performance on constrained robotics tasks.
CQL (ReDS) learns from varied driving behaviors, improving offline RL performance.
problem Learning from datasets with non-uniform variability in behavior policies.
method Reweighting the data distribution to allow per-state flexibility in following the behavior policy.
result CQL (ReDS) improves performance in various offline RL tasks.
This paper investigates how to efficiently transition and update policies, trained initially with demonstrations, using off-policy actor-critic reinforcement learning. It is well-known that techniques based on Learning from Demonstrations, for example behavior cloning, can lead to proficient policies given limited data…
Study strategic dynamic pricing for buyers with unknown manipulation costs.
problem Strategic buyers manipulate their features to get lower prices, hindering profit maximization.
method Proposes a strategic dynamic pricing policy that incorporates strategic behavior and binary response data.
result Achieves sublinear regret bound of compared to linear regret of non-strategic policies.
Deep learning analyzes healthcare provider actions and patient outcomes.
problem Understanding provider behavior in non-randomized healthcare settings.
method Deep causal behavioral policy learning (DC-BPL) using transformer architecture.
result Optimal provider policies identified for specific patient types.
KL-regularized RL from expert demos can lead to slow, unstable learning.
problem Pathological training dynamics in KL-regularized RL from expert demonstrations.
method Empirical analysis and non-parametric behavioral reference policies.
result KL-regularized RL can be significantly improved by using non-parametric behavioral policies.
New estimator GMIPS reduces variance in ranking policy evaluation.
problem High variance in off-policy evaluation for ranking policies.
method GMIPS estimator with user behavior model on ranking embedding spaces.
result GMIPS achieves lowest MSE and balances bias-variance trade-off.
We study the problem of off-policy policy optimization in Markov decision processes, and develop a novel off-policy policy gradient method. Prior off-policy policy gradient approaches have generally ignored the mismatch between the distribution of states visited under the behavior policy used to collect data, and what …
We consider off-policy policy evaluation when the trajectory data are generated by multiple behavior policies. Recent work has shown the key role played by the state or state-action stationary distribution corrections in the infinite horizon context for off-policy policy evaluation. We propose estimated mixture policy …
This paper solves steady-state planning for multichain MDPs.
problem Specifying constraints on the steady-state behavior of an agent.
method Linear programming solution for multichain MDPs.
result Optimal solutions yield stationary policies with rigorous guarantees.
Method learns evolving policies in healthcare contexts.
problem Understanding non-stationary behavior in evolving decision-making processes.
method Inverse Contextual Bandits (ICB) approach for learning interpretable representations of non-stationary behavior.
result Demonstrated applicability and accuracy of ICB method in liver transplantation policies.
Study improves off-policy evaluation from non-i.i.d. bandit samples.
problem Improving off-policy evaluation from non-independent bandit samples.
method Constructing an estimator from a standardized martingale difference sequence.
result Proposed estimator performs better than existing methods.
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 proposes a method to improve off-policy reinforcement learning in batch settings.
problem Challenges in applying off-policy reinforcement learning to batch data.
method Uses a learned prior, the advantage-weighted behavior model (ABM), to bias RL policies.
result Improves performance on various RL tasks, including robot control.
BRPO optimizes batch RL policies to better exploit state-action differences.
problem Batch RL's conservatism limits exploitation of state-action differences.
method Proposes residual policies and derives BRPO to maximize policy performance.
result BRPO achieves state-of-the-art performance in various tasks.
New algorithm learns policies without uniform overlap assumption.
problem Learning optimal policies from non-uniformly collected data.
method Pessimistic Policy Learning (PPL) using lower confidence bounds.
result Efficient policy learning for adaptively collected data.
Adapts safe policies for exploration in high-risk settings.
problem Balancing safety and exploration in high-risk environments.
method Uses conformal calibration on a safe reference policy to determine aggressive action limits.
result Safe exploration improves performance without requiring model class identification or hyperparameter tuning.
New method recovers diverse policies from expert data using state-action pair weighting.
problem Recovering diverse policies from expert trajectories.
method Pointwise mutual information weighted behavioral cloning.
result Effective in focusing on state-action pairs most representative of the style.
A new framework for adaptive behavior using reusable value profiles.
problem Adaptive behavior in changing environments requires switching among value-control regimes, but maintaining separate parameters for each situation is impractical.
method Introduces value profiles: reusable bundles of parameters assigned to hidden states, allowing for state-conditional strategy recruitment without independent parameters for each context.
result Profile-based models outperform simpler alternatives in probabilistic reversal learning, suggesting belief-dependent control of adaptive behavior.
New method improves reinforcement learning generalization.
problem Few environments lead to poor generalization in reinforcement learning.
method Integrates sequential structure into representation learning, using a policy similarity metric (PSM) and contrastive embeddings (PSEs).
result PSEs improve generalization across various benchmarks.
Dual behavior policy improves reinforcement learning across various environments.
problem Challenges in reinforcement learning with inconsistent or unknown environments.
method Dual, advantage-based behavior policy using counterfactual regret minimization.
result Demonstrated improved performance over baseline models in diverse environments.
Behavior Transfer improves reinforcement learning by leveraging pre-trained policies.
problem Efficient transfer of knowledge in reinforcement learning.
method Behavior Transfer (BT) that uses pre-trained policies for exploration.
result BT combined with pre-training leads to better solutions than without pre-training.
SafeMIL learns safer policies by avoiding risky behavior from non-preferred trajectories.
problem Learning safe imitation policies from non-preferred trajectories in risky environments.
method SafeMIL uses Multiple Instance Learning to learn a cost function from non-preferred trajectories.
result SafeMIL learns a safer policy that avoids non-preferred behaviors without sacrificing reward performance.
When we implement a portfolio selection methodology under a mean-risk formulation, it is essential to correctly model investors' risk aversion which may be time-dependent, or even state-dependent during the investment procedure. In this paper, we propose a behavior risk aversion model, which is a piecewise linear funct…
We study the problem of controllable generation of long-term sequential behaviors, where the goal is to calibrate to multiple behavior styles simultaneously. In contrast to the well-studied areas of controllable generation of images, text, and speech, there are two questions that pose significant challenges when genera…
Experience replay (ER) is a fundamental component of off-policy deep reinforcement learning (RL). ER recalls experiences from past iterations to compute gradient estimates for the current policy, increasing data-efficiency. However, the accuracy of such updates may deteriorate when the policy diverges from past behavio…
Compressed imitation learning uses simplicity priors for efficient expert behavior copying.
problem Efficiently learn expert behaviors with minimal data.
method Utilizes policy simplicity as a prior for sample-efficient imitation learning.
result Significantly higher scores achieved with limited expert demonstrations.
One-step policy improvement outperforms iterative RL methods on D4RL.
problem Improving offline RL without off-policy evaluation.
method One-step constrained/regularized policy improvement using on-policy Q estimates.
result One-step algorithm outperforms iterative algorithms on D4RL benchmark.
Study how untrained policies explore in RL environments.
problem Challenges in reinforcement learning, especially sparse or adversarial reward structures.
method Theoretical and empirical analysis of untrained deep neural policies in a toy model.
result Untrained policies generate correlated actions and non-trivial state-visitation distributions.
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.
Paper tackles covariate shift in offline IL using less proficient behavior data.
problem Mitigating covariate shift in Imitation Learning with limited data coverage.
method Model-based IL from Offline Data (MILO) framework.
result MILO can combat covariate shift even with sub-optimal behavior policy data.
Interpole learns transparent decision-making policies from data.
problem Understanding human decision-making in opaque environments.
method Interpole combines belief-update and belief-action mapping estimation.
result Interpole provides interpretable models of decision-making behavior.
We study how the behavior of deep policy gradient algorithms reflects the conceptual framework motivating their development. To this end, we propose a fine-grained analysis of state-of-the-art methods based on key elements of this framework: gradient estimation, value prediction, and optimization landscapes. Our result…
Unified framework for policy learning using weak supervision.
problem High-quality supervision is often infeasible or expensive in practice.
method Treat weak supervision as imperfect peer information and evaluate policies based on correlated agreement.
result Substantial performance improvements, especially in complex or noisy environments.
VA-OPE improves OPE by incorporating variance information, achieving tighter error bounds.
problem Estimating value function of a target policy from offline data collected by a behavior policy.
method Proposes VA-OPE, an algorithm that reweights Bellman residual using estimated variance of the value function.
result Achieves a tighter error bound than the best-known result.
In this work, we propose a method for learning driver models that account for variables that cannot be observed directly. When trained on a synthetic dataset, our models are able to learn encodings for vehicle trajectories that distinguish between four distinct classes of driver behavior. Such encodings are learned wit…
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…
Reinforcement learning agents need exploratory behaviors to escape from local optima. These behaviors may include both immediate dithering perturbation and temporally consistent exploration. To achieve these, a stochastic policy model that is inherently consistent through a period of time is in desire, especially for t…