No article text was recorded for this version.
non-convex reward landscapes
Version 1 of 132 papers38 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A Homotopic Approach to Policy Gradients for Linear Quadratic Regulators with Nonlinear Controls
- Blog: Automatic Reward Shaping from Multi-Objective Human Heuristics
- Blog: Understanding the Impact of Entropy on Policy Optimization
- Blog: Policy Gradient Algorithms Implicitly Optimize by Continuation
- Blog: Global Convergence of Direct Policy Search for State-Feedback $\mathcal{H}_\infty$ Robust Control: A Revisit of Nonsmooth Synthesis with Goldstein Subdifferential
- Blog: Policy Gradient with Tree Search (PGTS) in Reinforcement Learning Evades Local Maxima
- Blog: Iterative Model Refinement of Recommender MDPs Based on Expert Feedback
- Blog: Global Optimality Guarantees for Policy Gradient Methods
- Blog: Actor-Critic without Actor
- Blog: Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization
- Blog: An online prediction algorithm for reinforcement learning with linear function approximation using cross entropy method
- Blog: Accelerated Policy Gradient: On the Convergence Rates of the Nesterov Momentum for Reinforcement Learning
- Blog: BayRnTune: Adaptive Bayesian Domain Randomization via Strategic Fine-tuning
- Blog: Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs
- Blog: Logistic Q-Learning
- Blog: Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification
- Blog: Interactive Learning of Single-Index Models via Stochastic Gradient Descent
- Blog: A Unifying Perspective of Parametric Policy Search Methods for Markov Decision Processes
- Blog: Neural Trust Region/Proximal Policy Optimization Attains Globally Optimal Policy
- Blog: Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems
- Blog: Accelerated Policy Gradient: On the Nesterov Momentum for Reinforcement Learning
- Blog: Natural Policy Gradient Primal-Dual Method for Constrained Markov Decision Processes
- Blog: Difference of Convex Functions Programming for Reinforcement Learning
- Blog: The Geometry of Robust Value Functions
- Blog: Performance guarantees for policy learning
- Blog: Landscape of Policy Optimization for Finite Horizon MDPs with General State and Action
- Blog: Continuous Optimization for Feature Selection with Permutation-Invariant Embedding and Policy-Guided Search
- Blog: How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?
- Blog: Geometry and convergence of natural policy gradient methods
- Blog: A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence
- Blog: A Boosting Approach to Reinforcement Learning
- Blog: Riemannian Manifold Learning for Stackelberg Games with Neural Flow Representations
History & citation
Current · Permanent link
- This direction split from Non-Convex Optimization and Geometry in Reinforcement Learning (53% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_non_convex_reward_landscapes_8a999a63,
title = {non-convex reward landscapes},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-convex-reward-landscapes/rdr_8a999a63463a46e4903f6457a46898c3},
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_non_convex_reward_landscapes_8a999a63_v1,
title = {non-convex reward landscapes},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/non-convex-reward-landscapes/rdr_8a999a63463a46e4903f6457a46898c3/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}