NEO is a probabilistic neural model that induces compositional programs as a learned Language of Thought from non-textual observations and executes them via a shared transition model to enable explanation-driven generalization.
Why does hierarchy (sometimes) work so well in reinforcement learning?
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
A hierarchical framework extracts implicit safety criteria from crowd preferences and composes them via high-level policy to reduce safety violations in downstream RL tasks without explicit safety rewards.
Hybrid agent with variational quantum circuits for feature extraction in hierarchical RL outperforms classical baselines with 66% parameter savings, but quantum value estimation degrades results.
DIPPER uses bi-level optimization and DPO to train the higher-level policy from stationary preference comparisons and value regularization, claiming up to 40% gains on robotic navigation and manipulation tasks while introducing metrics for non-stationarity and infeasible subgoals.
SSE improves long-horizon goal-conditioned RL by using failure and partial-success transitions to identify unreliable subgoals, streamline high-level planning, and outperform prior hierarchical methods on benchmarks.
citing papers explorer
-
Learning to Theorize the World from Observation
NEO is a probabilistic neural model that induces compositional programs as a learned Language of Thought from non-textual observations and executes them via a shared transition model to enable explanation-driven generalization.
-
Implicit Safety Alignment from Crowd Preferences
A hierarchical framework extracts implicit safety criteria from crowd preferences and composes them via high-level policy to reduce safety violations in downstream RL tasks without explicit safety rewards.
-
Quantum Hierarchical Reinforcement Learning via Variational Quantum Circuits
Hybrid agent with variational quantum circuits for feature extraction in hierarchical RL outperforms classical baselines with 66% parameter savings, but quantum value estimation degrades results.
-
Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach
DIPPER uses bi-level optimization and DPO to train the higher-level policy from stationary preference comparisons and value regularization, claiming up to 40% gains on robotic navigation and manipulation tasks while introducing metrics for non-stationarity and infeasible subgoals.
-
Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning
SSE improves long-horizon goal-conditioned RL by using failure and partial-success transitions to identify unreliable subgoals, streamline high-level planning, and outperform prior hierarchical methods on benchmarks.