Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning

arXiv:2407.07631 · cs.LG, math.OC, math.ST, stat.ML, stat.TH · Submitted 2024-07-10 · Read on arXiv

cs.LG, math.OC, math.ST, stat.ML, stat.TH

Submitted: 2024-07-10

Updated: 2024-07-10

Terminology

• Reinforcement Learning — 79× in this paper · explained in 4 episodes
• Regret — 7× in this paper · explained in 3 episodes
• Reward Function — 6× in this paper · explained in 2 episodes
• Risk-Sensitive Pessimistic Value Iteration — 6× in this paper
• Sample Complexity — 6× in this paper · explained in 15 episodes
• Actor — 4× in this paper · explained in 3 episodes
• Markov Decision Process — 4× in this paper
• Representation Learning — 4× in this paper · explained in 2 episodes
• Consistency — 3× in this paper · explained in 3 episodes
• Theoretical Guarantees — 3× in this paper · explained in 2 episodes
• Markov Decision Process (MDP) — 2× in this paper · explained in 11 episodes
• Q-learning — 2× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 2× in this paper · explained in 25 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Adaptive Sampling — 1× in this paper · explained in 1 episode
• Adaptive sampling strategy — 1× in this paper · explained in 1 episode
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Online Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Recent Advances in Reinforcement Learning in Finance
• Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback
• Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning
• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
• Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds
• DSAC: Distributional Soft Actor-Critic for Risk-Sensitive Reinforcement Learning
• Near-Minimax-Optimal Risk-Sensitive Reinforcement Learning with CVaR
• What are the Statistical Limits of Offline RL with Linear Function Approximation?
• Risk-sensitive Markov Decision Process and Learning under General Utility Functions
• Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game
• Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage
• Representation Learning for Online and Offline RL in Low-rank MDPs
• Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism
• Risk-Averse Offline Reinforcement Learning
• Model-based Deep Reinforcement Learning for Dynamic Portfolio Optimization
• Is Risk-Sensitive Reinforcement Learning Properly Resolved?
• Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity
• Provably Efficient CVaR RL in Low-rank MDPs
• Nonstationary Reinforcement Learning with Linear Function Approximation

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks