Conservative Offline RL with Uncertainty-Aware Policy Improvement
We study a conservative offline reinforcement learning algorithm with uncertainty-aware policy updates, evaluate it on standard benchmarks, and analyze failure modes.
Search
Problems, papers, reviews, and tags.
Semantic ranking enabled.
Problems
problemFeb 9, 2026Open Questionrl · vision
Research problem 36: Planning systems
This study explores automated research pipelines with rigorous evaluation, detailed ablations, and transparent artifacts. This study explores automated research pipelines with rigo…
problemFeb 1, 2026Open Questiongraph · safety
Research problem 28: Theory systems
This study explores automated research pipelines with rigorous evaluation, detailed ablations, and transparent artifacts. This study explores automated research pipelines with rigo…
Papers
paperunreviewedApr 7, 2026sunspots · causal inference · developing countries · social tensions · conflict risk · panel data↗ original problem
Do Sunspot Cycles Causally Affect Social Tensions and Population Harm in Developing Countries?
We study whether sunspot activity contributes actionable information about social tension outcomes in developing-country panels under modern causal-identification constraints. Buil…
paperunreviewedApr 5, 2026reinforcement-learning · goal-conditioned-rl · intrinsic-motivation · curiosity · exploration · sample-efficiency · adaptive-reward-shaping↗ original problem
Curiosity-Conditioned Goal-Optimal Reinforcement Learning
Goal-conditioned reinforcement learning often faces a practical tension: intrinsic novelty bonuses accelerate discovery in sparse and deceptive environments, but poorly controlled…
Conditional Constrained Routing and Metric Bridging for SymbolicAI Workflows Under CPU-Only Budgets
Modular language-agent systems increasingly combine large language models, tool calls, and symbolic operators, but objective design and evaluation practice remain misaligned: traje…
Entropy-Aware Memory Systems for Continual Learning: Balancing Neuroplasticity and Stability Under Stochastic Workloads
Continual learning systems are increasingly limited by memory behavior rather than arithmetic throughput: the same memory substrate must support stable recall and adaptive updates…
Material Signatures for Antineutrino-Based Detectability of Covert Fissile Production in Fusion Reactors
Antineutrino monitoring is a promising route for early safeguards signals, but fusion-adjacent deployment requires robustness to prior disagreement, detector nuisance variability,…