Minimum-flow GFlowNets on graphs encode optimal transport plans, with the learned policy recovering the optimal coupling between source and target distributions.
hub
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
An RL-guided MCTS proof search for Tamarin finds more and shorter proofs than standard search across 16 protocol models.
PMCTS is a new parallel MCTS variant that preserves formal policy improvement guarantees and scales with parallel compute, outperforming heuristic baselines in tested domains.
Inverse-RPO derives two variance-aware prior-based UCT policies from UCB-V that outperform PUCT on benchmarks with no extra cost.
Geometry-aware MCTS with incremental constraint updates and symmetry pruning yields new best-known configurations for five of six tested combinatorial geometry problems, including ~1.8n points for Max-N3IL on grids 82-119.
ARC-RL is a new suite of four MuJoCo continuous-control environments featuring game-inspired hexapod and quadruped morphologies, a single closed-form multi-component reward function, CPG demonstrators, and empirical comparisons of online and offline-to-online RL algorithms.
A single-qubit quantum reinforcement learning agent solves CartPole faster than classical networks and quantifies shot-count versus control-frequency requirements for real-time closed-loop control on NISQ hardware, including direct electronics programming to reduce latency.
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.
Coarse-to-fine 1D token sequences in autoregressive models enable stronger test-time search and even training-free text-to-image generation guided by verifiers, outperforming traditional 2D grid tokenization.
Aristotle reaches gold-medal-equivalent performance on 2025 IMO problems via integrated Lean proof search, informal lemma formalization, and a dedicated geometry solver.
Transformer RL with a Policy Model and Action Sampler finds UTM safety vulnerabilities 8x more efficiently than expert testing in 700-hour simulations.
RQGM enables co-evolution of agents and evaluators across epochs with non-stationary utilities, reporting gains in coding pass rates, paper acceptance, and proof grading over prior self-improving agents.
FactorLibrary stores reusable subexpressions to help RL agents (especially PPO+MCTS top-down) find certified optimal arithmetic circuits for polynomials up to complexity 8 at 91.8% success rate.
GIFT fine-tunes deep RL policies with a stability-focused reward to improve global stability while preserving task performance.
An empirical study of JEPA world models identifies architecture, training objective, and planning choices that yield a model outperforming DINO-WM and V-JEPA-2-AC on navigation and manipulation tasks.
Supervised learning across AI systems vindicates a uniform error-driven associationism for cognition, though operating inside advanced computational structures beyond classical associationist models.
Periodically re-centering the KL-regularizer on the current policy in self-play yields a policy-gradient algorithm that, in its exact form, provably converges to a Nash equilibrium.
A tutorial that unifies explicit and implicit world models through shared predictive structure for applications in physical AI such as robotics.
Advocates developing high-quality open-source scheduling software and linking observation planning with data analysis for future astronomical surveys.
Empirical tests in VizDoom show multiple DQN updates per step do not improve performance after learning rate adjustment, with a 4:1 update-to-step ratio optimal before significant degradation.
citing papers explorer
-
Your GFlowNet Secretly Learns an Optimal Transport Plan
Minimum-flow GFlowNets on graphs encode optimal transport plans, with the learned policy recovering the optimal coupling between source and target distributions.
-
Less Effort, Shorter Proofs: Reinforcement Learning for Security Protocol Analysis in Tamarin
An RL-guided MCTS proof search for Tamarin finds more and shorter proofs than standard search across 16 protocol models.
-
PMCTS: Particle Monte Carlo Tree Search for Principled Parallelized Inference Time Scaling
PMCTS is a new parallel MCTS variant that preserves formal policy improvement guarantees and scales with parallel compute, outperforming heuristic baselines in tested domains.
-
Variance-Aware Prior-Based Tree Policies for Monte Carlo Tree Search
Inverse-RPO derives two variance-aware prior-based UCT policies from UCB-V that outperform PUCT on benchmarks with no extra cost.
-
Geometry-Aware MCTS for Extremal Problems in Combinatorial Geometry
Geometry-aware MCTS with incremental constraint updates and symmetry pruning yields new best-known configurations for five of six tested combinatorial geometry problems, including ~1.8n points for Max-N3IL on grids 82-119.
-
ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders
ARC-RL is a new suite of four MuJoCo continuous-control environments featuring game-inspired hexapod and quadruped morphologies, a single closed-form multi-component reward function, CPG demonstrators, and empirical comparisons of online and offline-to-online RL algorithms.
-
Towards Real-time Control of a CartPole System on a Quantum Computer
A single-qubit quantum reinforcement learning agent solves CartPole faster than classical networks and quantifies shot-count versus control-frequency requirements for real-time closed-loop control on NISQ hardware, including direct electronics programming to reduce latency.
-
Evaluation-driven Scaling for Scientific Discovery
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.
-
(1D) Ordered Tokens Enable Efficient Test-Time Search
Coarse-to-fine 1D token sequences in autoregressive models enable stronger test-time search and even training-free text-to-image generation guided by verifiers, outperforming traditional 2D grid tokenization.
-
Aristotle: IMO-level Automated Theorem Proving
Aristotle reaches gold-medal-equivalent performance on 2025 IMO problems via integrated Lean proof search, informal lemma formalization, and a dedicated geometry solver.
-
Revealing Safety-Critical Scenarios for UTM via Transformer
Transformer RL with a Policy Model and Action Sampler finds UTM safety vulnerabilities 8x more efficiently than expert testing in 700-hour simulations.
-
The Red Queen G\"odel Machine: Co-Evolving Agents and Their Evaluators
RQGM enables co-evolution of agents and evaluators across epochs with non-stationary utilities, reporting gains in coding pass rates, paper acceptance, and proof grading over prior self-improving agents.
-
FactorLibrary: From Polynomials to Circuits via Recursive Subgoals
FactorLibrary stores reusable subexpressions to help RL agents (especially PPO+MCTS top-down) find certified optimal arithmetic circuits for polynomials up to complexity 8 at 91.8% success rate.
-
GIFT: Global stabilisation via Intrinsic Fine Tuning
GIFT fine-tunes deep RL policies with a stability-focused reward to improve global stability while preserving task performance.
-
What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
An empirical study of JEPA world models identifies architecture, training objective, and planning choices that yield a model outperforming DINO-WM and V-JEPA-2-AC on navigation and manipulation tasks.
-
The New Associationism: Lessons from Deep Learning
Supervised learning across AI systems vindicates a uniform error-driven associationism for cognition, though operating inside advanced computational structures beyond classical associationist models.
-
NashPG: A Policy Gradient Method with Iteratively Refined Regularization for Finding Nash Equilibria
Periodically re-centering the KL-regularizer on the current policy in self-play yields a policy-gradient algorithm that, in its exact form, provably converges to a Nash equilibrium.
-
A Tutorial on World Models and Physical AI
A tutorial that unifies explicit and implicit world models through shared predictive structure for applications in physical AI such as robotics.
-
Scheduling Discovery in the 2020s
Advocates developing high-quality open-source scheduling software and linking observation planning with data analysis for future astronomical surveys.
-
Optimal Use of Experience in First Person Shooter Environments
Empirical tests in VizDoom show multiple DQN updates per step do not improve performance after learning rate adjustment, with a 4:1 update-to-step ratio optimal before significant degradation.