No article text was recorded for this version.
value function polytope
Version 1 of 124 papers33 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Learning all optimal policies with multiple criteria
- Blog: A Geometric Traversal Algorithm for Reward-Uncertain MDPs
- Blog: How to Find the Exact Pareto Front for Multi-Objective MDPs?
- Blog: Multi-Objective Reinforcement Learning: Convexity, Stationarity and Pareto Optimality
- Blog: Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis
- Blog: Linear Fitted-Q Iteration with Multiple Reward Functions
- Blog: Multi-Objective Reinforcement Learning for Designing Ethical Environments
- Blog: Successor Feature Sets: Generalizing Successor Representations Across Policies
- Blog: Flexible Decomposition Algorithms for Weakly Coupled Markov Decision Problems
- Blog: The Multi-Objective Polynomial Optimization
- Blog: Game-Theoretic Learning Using the Imprecise Dirichlet Model
- Blog: Near-Minimax Multi-Objective RL under Predictable Adversarial Preferences and Preference-Free Exploration in Linear MDPs
- Blog: Beyond Winning and Losing: Modeling Human Motivations and Behaviors with Vector-Valued Inverse Reinforcement Learning
- Blog: Inverse Reinforcement Learning through Policy Gradient Minimization
- Blog: The Value Function Polytope in Reinforcement Learning
- Blog: Multi-objective Model Checking of Markov Decision Processes
- Blog: Online Learning and Blackwell Approachability with Partial Monitoring: Optimal Convergence Rates
- Blog: Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer
- Blog: The Information Geometry of Unsupervised Reinforcement Learning
- Blog: Geometric Policy Iteration for Markov Decision Processes
- Blog: Efficient Methods for Multi-Objective Decision-Theoretic Planning
- Blog: Public projects, Boolean functions and the borders of Border's theorem
- Blog: MAP: Multi-Human-Value Alignment Palette
- Blog: Instilling moral value alignment by means of multi-objective reinforcement learning
History & citation
Current · Permanent link
- The Convex Geometry of Multi-Objective Pareto Fronts merged into this direction (62% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_value_function_polytope_37444e04,
title = {value function polytope},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/value-function-polytope/rdr_37444e04f1b24a90829e84da6ced3170},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_value_function_polytope_37444e04_v1,
title = {value function polytope},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/value-function-polytope/rdr_37444e04f1b24a90829e84da6ced3170/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}