Paper analyzes model usage in policy optimization, improving sample efficiency and performance.
problem Balancing ease of data generation with model bias in reinforcement learning.
method Formulated and analyzed model-based reinforcement learning algorithm with empirical model generalization.
result Simple model-based approach outperforms existing methods in sample efficiency and asymptotic performance.
Lo-Hp decouples weight generation into local and global policies to improve flexibility and efficiency.
problem Over-coupling and long-horizon issues in current optimization methods.
method Hybrid-Policy Sub-Trajectory Balance objective.
result Learning local optimization policies addresses long-horizon issues and enhances global weight generation.
Model-based RL with adversarial training for efficient recommendation policies.
problem Expensive model learning in model-free RL for recommender systems.
method Generative adversarial network for offline policy learning, discriminator for reward scaling and model bias reduction.
result Effective policy learning from offline and generated data, reducing bias in the learned model.
New method improves policies by combining Markov and non-Markov strategies.
problem Improving policies in reinforcement learning.
method Geometric Policy Composition (GPI) using a geometric horizon model (GHM).
result GPI can improve non-Markov policies by composing GHMs of base Markov policies.
MoMA improves model-based RL by using unrestricted policy classes.
problem Limited sample efficiency and generalizability in model-based offline RL.
method Model-based mirror ascent algorithm with general function approximations.
result Theoretical guarantees and practical implementation of MoMA.
New GFlowNet training framework using policy gradients for combinatorial object generation.
problem Training efficiency and robustness in GFlowNet models.
method Policy-dependent rewards and coupled training strategy for forward and backward policies.
result Advanced RL perspectives for robust gradient estimation improve GFlowNet performance.
Proposes a Riemannian optimization for policy improvement in MDPs.
problem Optimizing policy functions in Markov decision processes (MDPs).
method Riemannian proximal optimization algorithm with Gaussian mixture model (GMM).
result Guaranteed convergence and efficacy demonstrated in preliminary experiments.
Adapts model-based advice to stabilize black-box policies for nonlinear control.
problem Stabilizing machine-learned policies for nonlinear control with limited model information.
method Proposes an adaptive λ-confident policy to combine black-box and model-based advice. result Proves the stability of the adaptive λ-confident policy and its competitive ratio. Paper introduces effect-invariance for better policy generalization.
problem Adapting policies to unseen environments efficiently.
method Introduces effect-invariance, a relaxation of full invariance, and develops testing procedures to test e-invariance directly from data.
result Effect-invariance enables zero-shot and few-shot policy generalization without assuming a causal graph.
Efficient policy learning from observational data using weighted classification reductions.
problem Efficient policy evaluation does not necessarily lead to efficient estimation of policy parameters.
method Proposed an estimation approach based on generalized method of moments, efficient for policy parameters.
result Demonstrated empirical efficiency and regret benefits of a proposed method.
Double descent found in DRL, improving generalization with model capacity.
problem Generalization in over-parameterized DRL models.
method Actor-Critic framework, Policy Entropy metric.
result Policy Entropy significantly reduces as model capacity increases, indicating improved generalization.
We study the problem of off-policy policy evaluation (OPPE) in RL. In contrast to prior work, we consider how to estimate both the individual policy value and average policy value accurately. We draw inspiration from recent work in causal reasoning, and propose a new finite sample generalization error bound for value e…
A method to learn robust policies for environments with model mismatches.
problem Training agents in high-stakes scenarios with mismatched training and real environments.
method Formalizes the perturbation as a zero-sum game to find Nash Equilibrium, which corresponds to the robust policy.
result Our algorithm can find a near-optimal robust policy with high probability using polynomial samples.
Proposes a new framework to optimize policies while accounting for model uncertainty.
problem Model-based reinforcement learning's vulnerability to model bias and inefficiency.
method Uncertainty-aware model-based policy optimization framework.
result Significantly lower sample complexity and competitive asymptotic performance.
Policy analysts wish to visualize a range of policies for large simulator-defined Markov Decision Processes (MDPs). One visualization approach is to invoke the simulator to generate on-policy trajectories and then visualize those trajectories. When the simulator is expensive, this is not practical, and some method is r…
The paper tackles robust reinforcement learning with performance guarantees.
problem Finding a robust policy for RMDP with state space uncertainties.
method Proposes RLSPI algorithm for learning optimal robust policy with performance bounds.
result Demonstrates the performance of RLSPI on standard benchmark problems.
PC-PG balances exploration and exploitation in reinforcement learning.
problem Local policy gradient methods struggle with exploration.
method PC-PG uses an ensemble of learned policies (policy cover) to balance exploration and exploitation.
result PC-PG provides strong theoretical guarantees and empirical validation.
In sequence generation task, many works use policy gradient for model optimization to tackle the intractable backpropagation issue when maximizing the non-differentiable evaluation metrics or fooling the discriminator in adversarial learning. In this paper, we replace policy gradient with proximal policy optimization (…
Learning policies on data synthesized by models can in principle quench the thirst of reinforcement learning algorithms for large amounts of real experience, which is often costly to acquire. However, simulating plausible experience de novo is a hard problem for many complex environments, often resulting in biases for …
Study off-policy evaluation in partially observable environments, reducing bias and errors.
problem Bias and large errors in off-policy evaluation for partially observable environments.
method Defined and solved off-policy evaluation for POMDPs, introduced Decoupled POMDP model.
result Demonstrated and compared off-policy evaluation methods, showing benefits of new approach.
New method optimizes policies without assuming known link functions between preferences and rewards.
problem Policy alignment with unknown and unrestricted link functions.
method Formulates an f-divergence-constrained reward maximization problem, learning policies directly. result Induces a semiparametric single-index binary choice model for policy alignment.
POTEC tackles off-policy learning in large action spaces, improving effectiveness.
problem Existing OPL methods fail in large discrete action spaces due to bias or variance issues.
method Two-stage algorithm: cluster selection via policy-based approach, action selection via regression-based approach.
result POTEC provides substantial improvements in off-policy learning effectiveness, especially in large and structured action spaces.
Procedure for evaluating RL policies in risky settings.
problem Identifying risky episodes in RL policy applications.
method Gumbel-Max SCMs for generating counterfactual trajectories.
result Identifies episodes with dramatic counterfactual reward differences.
VMBPO optimizes model and policy jointly using variational lower-bound.
problem Data efficiency in RL with biased simulated data.
method Formulate variational objective function, use EM, iteratively improve model and policy.
result VMBPO is more sample-efficient and robust than model-free algorithms.
Proposes a conservative exploration method for RL agents.
problem Guaranteeing performance of exploratory policies in RL.
method Importance sampling for off-policy policy evaluation.
result Derives a regret bound ensuring no conservative constraint violation.
Improves data efficiency in multi-agent control tasks using model-based reinforcement learning.
problem Limited data efficiency in reinforcement learning for multi-agent tasks.
method Decentralized model-based policy optimization (DMPO) framework.
result DMPO achieves superior data efficiency and matches model-free methods using true models.
Study shows sample complexity for learning optimal policies in SSP with generative model.
problem Learning optimal policies in Stochastic Shortest Path problems.
method Derive and prove lower and upper bounds on sample complexity.
result Lower bound of Ω(SAB⋆3/(cminε2)) samples for general case, and up to logarithmic factors for bounded hitting time condition. We study a reinforcement learning setting, where the state transition function is a convex combination of a stochastic continuous function and a deterministic function. Such a setting generalizes the widely-studied stochastic state transition setting, namely the setting of deterministic policy gradient (DPG). We firstl…
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.
New method fine-tunes discrete diffusion models for RLHF tasks.
problem Fine-tuning discrete diffusion models with policy gradient methods is challenging.
method Proposed SEPO algorithm for efficient fine-tuning over non-differentiable rewards.
result Numerical experiments show scalability and efficiency of SEPO.
CPR models complex decision processes by breaking them into context-specific policies, improving interpretability and accuracy.
problem Interpreting dynamic human decision-making processes in medical contexts.
method Develops Contextualized Policy Recovery (CPR) framework for multi-task learning, modeling each context-specific policy as a linear map.
result Achieves state-of-the-art performance in predicting medical decisions, closing the gap between interpretable and black-box methods.
Bayesian regularization improves policy performance in noisy MDPs.
problem Suboptimal policies from estimated model parameters.
method Bayesian regularization of MDP objective function with prior information.
result Regularized policies show better robustness against model noise.
The paper provides a non-asymptotic error bound for linear system identification under nonlinear policies.
problem System identification for linear systems with nonlinear and/or time-varying policies under i.i.d. random excitation noises.
method Least square estimation with non-asymptotic error bound for bounded state and action trajectories.
result The error bound is consistent with linear policies and generalizes existing guarantees.
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 generative recurrent neural network is quickly trained in an unsupervised manner to model popular reinforcement learning environments through compressed spatio-temporal representations. The world model's extracted features are fed into compact and simple policies trained by evolution, achieving state of the art resul…
New RL method reduces sample complexity for large policy spaces.
problem Large-scale RL with unknown optimal policies and state/action spaces.
method Introduces eluder dimension for policy space, proving near-optimal sample complexity.
result Near-optimal sample complexity upper bound that depends linearly on eluder dimension.
Generative ML learns optimal pursuit trajectories in pursuit-evasion games.
problem Optimizing Blue's pursuit trajectory to intercept Red in a game of pursuit-evasion.
method Applying generative machine learning to learn optimal action policies for Blue.
result Generative ML models can learn relevant representations for pursuit-evasion dynamics.
Framework learns robust control policies from expert demonstrations.
problem Adversarial robustness and closed-loop generalization in feedback control policies.
method Lipschitz-constrained loss minimization for certified robustness and generalization.
result Finite sample bound on policy learning error and robust closed-loop stability.
Text generation is a crucial task in NLP. Recently, several adversarial generative models have been proposed to improve the exposure bias problem in text generation. Though these models gain great success, they still suffer from the problems of reward sparsity and mode collapse. In order to address these two problems, …
SDM Policy accelerates inference for robotic tasks while maintaining high action quality.
problem Prolonged inference times in diffusion-based policies for high-frequency control tasks.
method Two-stage optimization: score matching and distribution matching; dual-teacher mechanism.
result 6x inference speedup with state-of-the-art action quality.
New RL algorithms improve control tasks with data reuse.
problem Real-world control requires performance guarantees and data efficiency.
method Generalized Policy Improvement combining on-policy guarantees and sample reuse.
result Extensive experimental analysis shows benefits of new algorithms.
The paper proposes a new policy for optimal treatment allocation based on quantile treatment effects.
problem Optimal treatment allocation policies that target distributional welfare, especially when individuals are heterogeneous.
method The approach involves allocating treatments based on the conditional quantile of individual treatment effects (QoTE), considering both prudent and negligent policymakers.
result The proposed minimax policies are robust to model uncertainty and can be generalized to various settings.
Study shows hard sample complexity for learning optimal policies in stochastic shortest path problems.
problem Learning optimal policies in stochastic shortest path problems.
method Analyzes sample complexity with and without generative models, derives lower and upper bounds.
result Proves sample complexity bounds and impossibility of horizon-free regret in SSPs.
The paper proposes a new method to estimate optimal policies using MCMC.
problem Estimating the optimal policy for systems with unknown dynamics and reward functions.
method Using Markov Chain Monte Carlo to generate samples from the posterior distribution of parameters conditioned on optimality.
result The method provably converges to the globally optimal stochastic policy with similar variance to policy gradient methods.
Embedding RL policies in RKHS for robustness and theoretical guarantees.
problem Stability and theoretical guarantees in RL policy representation.
method Low-dimensional embedding of RL policies in RKHS.
result Embedded policies maintain high return with strong theoretical guarantees.
SymNet uses neural models to solve RMDPs efficiently.
problem Limited effectiveness of generalized policies in RMDPs.
method SymNet trains shared parameters for an RDDL domain, converts instances to graphs, uses relational neural models for node embeddings, and scores actions based on embeddings.
result SymNet policies outperform random and state-of-the-art deep reactive policies on nine RDDL domains.
Framework improves policy generalizability under biased training data.
problem Learning policies that generalize to a target population from biased training data.
method Characterizes sample selection bias using a selection variable, optimizes minimax value over uncertainty set, derives efficient algorithm.
result Policies generalize to target population, outperform standard methods.
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.