Study optimality in safety-constrained Markov decision processes using asynchronous value iteration and modified Q-learning.
problem Optimality in safety-constrained Markov decision processes with multichain structure.
method Formulated as a zero-sum game, constructed asynchronous value iteration scheme and modified Q-learning algorithm.
result Resolved Bellman's principle of optimality for multichain Markov decision processes and provided learning algorithms.
Develops new reinforcement learning methods for complex constrained decision-making problems.
problem Complex constrained decision-making problems with a continuum of constraints.
method Proposes semi-infinitely constrained Markov decision processes (SICMDPs) and two reinforcement learning algorithms: SI-CRL and SI-CPO.
result Demonstrates the effectiveness of SI-CRL and SI-CPO in solving complex sequential decision-making tasks.
New RL approach tackles constrained Markov decision processes.
problem Applying RL to physical systems with safety constraints.
method Formulated as a Constrained Markov Decision Process (CMDP), introduced a safe policy improvement method.
result Agent learns to maximize returns while satisfying constraints.
A new algorithm finds optimal solutions for constrained decision processes.
problem Optimizing state-value functions with constraints in CMDPs.
method Gradient-Aware Search (GAS) exploiting PWLC structure.
result GAS converges faster and more reliably than existing methods.
New algorithm tackles constrained Markov decision processes with peak constraints.
problem Optimizing dynamic systems with peak constraints.
method Model-free algorithm converting PCMDP to unconstrained problem, applying Q-learning.
result Algorithm achieves ( ε , p ) (ε,p) ( ε , p ) -PAC policy under certain conditions. Paper uses RL to solve constrained combinatorial optimization problems.
problem Constrained combinatorial optimization problems.
method Extending NCO theory to CMDPs, using RL with penalty signals.
result Proposes a superior method for solving constrained problems.
New method optimizes costly evaluations in Bayesian optimization.
problem Costly evaluations in BO methods, especially in hyperparameter tuning.
method Formulated as a CMDP, developed rollout approximation for optimal policy.
result Improved cost efficiency over standard BO methods.
Study uses DRL with Lagrangian relaxation to solve temporal control tasks with STL constraints.
problem Optimal control problems with temporal logic constraints.
method Extended CMDP formulation, Lagrangian relaxation, two-phase constrained DRL algorithm.
result Demonstrated learning performance of the proposed algorithm through simulations.
Automated Budget Constrained Training optimizes model training under time constraints.
problem Balancing model quality and computational cost in constrained time.
method Developed a hyperparameter optimisation algorithm that learns the relationship between hyperparameters, model quality, and computational cost.
result The algorithm optimally decides whether to terminate or continue training, and what hyperparameters to use.
Study examines sample complexity for RL with safety constraints.
problem Ensuring safety in RL for systems with constraints.
method Analyzes two RL approaches: generative and online.
result Sample complexity increased by a logarithmic factor in constraints.
In order to satisfy safety conditions, an agent may be constrained from acting freely. A safe controller can be designed a priori if an environment is well understood, but not when learning is employed. In particular, reinforcement learned (RL) controllers require exploration, which can be hazardous in safety critical …
New algorithm achieves optimal regret in average reward MDPs without prior bias information.
problem Achieving optimal regret in average reward MDPs with computational efficiency and without prior bias information.
method Projective Mitigated Extended Value Iteration (PMEVI) to compute bias-constrained optimal policies efficiently.
result First tractable algorithm with minimax optimal regret of O ~ ( s p ( h ∗ ) S A T ) \widetilde{\mathrm{O}}(\sqrt{\mathrm{sp}(h^*) S A T}) O ( sp ( h ∗ ) S A T ) . Constrained Markov Decision Processes are a class of stochastic decision problems in which the decision maker must select a policy that satisfies auxiliary cost constraints. This paper extends upper confidence reinforcement learning for settings in which the reward function and the constraints, described by cost functi…
Solves online 3D bin packing with deep reinforcement learning under constraints.
problem Challenges of packing items immediately without information and constraints.
method Constrained deep reinforcement learning (DRL) with feasibility predictor.
result Significantly outperforms state-of-the-art methods in online 3D bin packing.
A Budgeted Markov Decision Process (BMDP) is an extension of a Markov Decision Process to critical applications requiring safety constraints. It relies on a notion of risk implemented in the shape of a cost signal constrained to lie below an - adjustable - threshold. So far, BMDPs could only be solved in the case of fi…
Survey of mathematical foundations for reinforcement learning.
problem Design and analysis of modern reinforcement learning algorithms.
method Organizes mathematical structures from probability, optimization, and operator theory.
result Unified mathematical entry point for researchers in various fields.
New algorithm reduces sample complexity for constrained MDPs.
problem Learning policies in constrained average-reward MDPs.
method Model-based algorithm for relaxed and strict feasibility settings.
result Achieves minimax-optimal bounds for constrained MDPs.
Algorithm reduces episode count for CMDPs with constraints.
problem Online decision-making with constraints in episodic CMDPs.
method Optimistic planning using linear programming for PAC guarantee.
result Probably approximately correct (PAC) guarantee on episode count.
New algorithm for reinforcement learning in uncertain environments with unknown thresholds.
problem Safety in reinforcement learning in unknown and uncertain environments.
method Growing-Window estimator sampling and Stochastic Pessimistic-Optimistic Thresholding (SPOT) algorithm.
result Achieves sublinear regret and constraint violation of i l d e O ( T ) ilde{\mathcal{O}}(\sqrt{T}) i l d e O ( T ) . New algorithm reduces regret in CMDPs without cancellation of errors.
problem Lagrangian approaches in CMDPs struggle with cancellation of errors.
method OptAug-CMDP, based on augmented Lagrangian method.
result Regret of i l d e O ( K ) ilde{O}(\sqrt{K}) i l d e O ( K ) for both objective and constraint violation. Paper proposes a model-free algorithm for CMDPs with long-term constraints, achieving optimal regret bounds.
problem Optimizing systems with long-term constraints where transition probabilities are unknown.
method Combines concepts from constrained optimization and Q-learning to propose an algorithm.
result Achieves optimal regret bounds for reward and constraint violation.
New algorithm solves uncertain Markov decision processes using Wasserstein uncertainty.
problem Solving Markov decision processes with uncertain transition probabilities.
method Distributionally robust Q Q Q -learning algorithm for Wasserstein uncertainty. result Convergence of the algorithm proved and demonstrated with real data.
Reward suffices for convex MDPs, expanding RL to new problems.
problem Capturing goals as convex functions of stationary distribution.
method Reformulated as a min-max game using Fenchel duality.
result Convex MDPs require non-stationary reward functions.
Many medical decision-making tasks can be framed as partially observed Markov decision processes (POMDPs). However, prevailing two-stage approaches that first learn a POMDP and then solve it often fail because the model that best fits the data may not be well suited for planning. We introduce a new optimization objecti…
New algorithm reduces sample complexity for safe reinforcement learning.
problem Safe reinforcement learning in constrained MDPs with performance and safety constraints.
method Model-based primal-dual algorithm balancing regret and bounded constraint violations.
result Proves near-optimal policies with bounded violations or zero violations in CMDPs.
New algorithm reduces regret and constraint violation in adversarial CMDP learning.
problem Online learning for episodic stochastically constrained Markov decision processes (CMDPs) with adversarial loss.
method Upper Confidence Primal-Dual Reinforcement Learning (UC-PDL) algorithm.
result Achieves O ~ ( L ∣ S ∣ ∣ A ∣ T ) \widetilde{\mathcal{O}}(L|\mathcal{S}|\sqrt{|\mathcal{A}|T}) O ( L ∣ S ∣ ∣ A ∣ T ) upper bounds of both regret and constraint violation. CPPO learns policies from partial offline data in MDPs with structural assumptions.
problem Offline Reinforcement Learning with partial coverage assumption.
method Constrained Pessimistic Policy Optimization (CPPO) using a function class and model class constraint.
result CPPO achieves PAC guarantee with partial coverage, learning competitive policies.
DR-RPO optimizes robust policies in RL with limited interaction, achieving sublinear regret.
problem Policy optimization in RL under distribution shift and adversarial dynamics.
method DR-RPO algorithm incorporating reference-policy regularization and upper confidence bonus for exploration.
result DR-RPO achieves sublinear regret and polynomial suboptimality bounds in robust RL.
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.
Style Miner generates stable and significant style factors for time series analysis.
problem Finding significant and stable explanatory factors in high-dimensional time series data.
method Proposes a reinforcement learning method to balance explanatory power and stability constraints.
result Outperforms existing methods by a large margin and achieves a 10% gain in R-squared explanatory power.
New algorithm solves constrained MDPs with generative model, reducing sample complexity.
problem Maximizing rewards while adhering to constraints in MDPs.
method Primal-dual framework using mirror descent value iteration.
result Near-optimal sample complexity bounds for CMDPs.
A new RL model ensures safe learning in uncertain environments.
problem Safe reinforcement learning in uncertain, partially observable environments.
method Lyapunov-based uncertainty quantification and Transformers for memory.
result Significant improvement in safety and optimality in grid-world tasks.
Paper presents an algorithm for optimal regret in communicating Markov decision processes.
problem Achieving optimal regret in Markov decision processes with a communicating assumption.
method The algorithm explicitly tracks the constant K(M) to learn optimally, balancing exploration, co-exploration, and exploitation.
result The algorithm achieves asymptotically optimal regret K ( M ) log ( T ) + o ( log ( T ) ) K(M) \log(T) + \mathrm{o}(\log(T)) K ( M ) log ( T ) + o ( log ( T )) for communicating Markov decision processes. New bounds for learning near-optimal policies in CMDPs with constraints.
problem Optimizing policies in CMDPs with constraints.
method Model-based algorithm addressing relaxed and strict feasibility.
result Near-optimal sample complexity bounds for CMDPs.
Advances in mobile computing technologies have made it possible to monitor and apply data-driven interventions across complex systems in real time. Markov decision processes (MDPs) are the primary model for sequential decision problems with a large or indefinite time horizon. Choosing a representation of the underlying…
The Markov assumption (MA) is fundamental to the empirical validity of reinforcement learning. In this paper, we propose a novel Forward-Backward Learning procedure to test MA in sequential decision making. The proposed test does not assume any parametric form on the joint distribution of the observed data and plays an…
Develops an actor-critic algorithm for risk-sensitive Markov decision processes.
problem Risk-sensitive cost criterion in Markov decision processes.
method Actor-critic algorithm with function approximation.
result Asymptotic convergence of the actor-critic algorithm.
We consider an agent who is involved in a Markov decision process and receives a vector of outcomes every round. Her objective is to maximize a global concave reward function on the average vectorial outcome. The problem models applications such as multi-objective optimization, maximum entropy exploration, and constrai…
Overview of risk-sensitive Markov decision processes with Optimized Certainty Equivalent.
problem Optimizing decision-making under risk in Markov processes.
method Analyzes risk-sensitive criteria using Optimized Certainty Equivalent, including entropic risk and Conditional Value-at-Risk.
result Conditions for the existence of optimal policies and solution procedures are provided.
ClauseLens uses reinforcement learning to price reinsurance treaties transparently and auditably.
problem Opaque and difficult-to-audit reinsurance treaty pricing practices.
method ClauseLens models treaty pricing as a Risk-Aware Constrained Markov Decision Process (RA-CMDP), incorporating legal clauses and generating interpretable explanations.
result ClauseLens reduces solvency violations and improves tail-risk performance, achieving 88.2% accuracy in clause-grounded explanations.
New learning process for neural classifiers simplifies decision weights.
problem Training decision layer weights in neural classifiers.
method Choosing appropriate loss functions and solving constrained optimization problems.
result A new learning process for pre-decision weights that is simple and effective.
Algorithm finds safe zones in policy Markov Decision Processes to limit trajectory escape.
problem Finding safe zones in policy Markov Decision Processes to limit trajectory escape.
method Bi-criteria approximation learning algorithm with polynomial sample complexity.
result Achieves almost 2 approximation for both escape probability and safe zone size.
Risk measures applied to dynamic Markov processes with varying risk aversion.
problem Investigating dynamic risk measures in Markov decision processes with varying risk aversion.
method Distributional viewpoint on law-invariant convex risk measures, applied to Markov decision processes with latent costs and random actions.
result Existence of optimal policies in finite and infinite time horizons under mild assumptions.
We address the problem of inverse reinforcement learning in Markov decision processes where the agent is risk-sensitive. In particular, we model risk-sensitivity in a reinforcement learning framework by making use of models of human decision-making having their origins in behavioral psychology, behavioral economics, an…
Bayesian method infers local rules for collective animal movement.
problem Learn local rules governing long-term group behaviors.
method Bayesian Inverse Reinforcement Learning with Linearly-Solvable Markov Decision Process.
result Recover true costs and find value of collective movement.
The paper tackles batch policy learning in Markov Decision Processes, focusing on average reward maximization.
problem Maximizing long-term average reward in Markov Decision Processes with batch learning.
method Doubly robust estimator for average reward, optimization algorithm for optimal policy, finite-sample regret guarantee.
result The proposed method achieves semiparametric efficiency and provides a finite-sample regret guarantee.
We establish geometric and topological properties of the space of value functions in finite state-action Markov decision processes. Our main contribution is the characterization of the nature of its shape: a general polytope (Aigner et al., 2010). To demonstrate this result, we exhibit several properties of the structu…
New algorithm identifies best policy in MDPs faster.
problem Identifying the best policy in Markov Decision Processes.
method Problem-dependent lower bound and first algorithm with instance-specific sample complexity.
result First algorithm with reduced exploration rate for faster convergence.