Paper
Publication
Generalised Policy Improvement with Geometric Policy Composition
Paper
Publication
Mastering Atari with Discrete World Models
Paper
Publication
Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban
Paper
Publication
Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions
Paper
Publication
Physically Embedded Planning Problems: New Challenges for Reinforcement Learning
Paper
Publication
Monte-Carlo Tree Search as Regularized Policy Optimization
Paper
Publication
Efficient Planning in Large MDPs with Weak Linear Function ApproximationEfficient Sample Collection Strategy for Reinforcement Learning
Paper
Publication
Expected Eligibility Traces
Paper
Publication
Pessimism About Unknown Unknowns Inspires Conservatism
Paper
Publication
Rapid Task-Solving in Novel Environments
Paper
Publication
Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning
Paper
Publication
Static and Dynamic Values of Computation in MCTS
Paper
Publication
Combining Q-Learning and Search with Amortized Value Estimates
Paper
Publication
Planning in entropy-regularized Markov decision processes and games
Paper
Publication
Iterative Budgeted Exponential Search
Paper
Publication
Direct Policy Gradients: Direct Optimization of Policies in Discrete Action Spaces
Paper
Publication
When to use parametric models in reinforcement learning?
Paper
Publication
Zooming Cautiously: Linear-Memory Heuristic Search With Node Expansion Guarantees
Paper
Publication
Interval Timing in Deep Reinforcement Learning Agents
Paper
Publication
Learning Compositional Neural Programs with Recursive Tree Search and Planning
Paper
Publication
COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration
Paper
Publication
A Bayesian Approach to Robust Reinforcement Learning
Paper
Publication
The StreetLearn Environment and Dataset
Paper
Publication
An investigation of model-free planning
Paper
Publication
Learning Latent Dynamics for Planning from Pixels