Search
On Oracle-Efficient PAC RL with Rich Observations
Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
Neural Information Processing Systems http://nips.cc/
Monte-Carlo Tree Search for Constrained POMDPs
Jongmin Lee, Geon-hyeong Kim, Pascal Poupart, Kee-Eung Kim
However, many real-world problems inherently have multiple goals, where multi-objective formulations are more natural.
Single-Agent Policy Tree Search With Guarantees
Laurent Orseau, Levi Lelis, Tor Lattimore, Theophane Weber
We introduce two novel tree search algorithms that use a policy to guide search.
On Learning Intrinsic Rewards for Policy Gradient Methods
Zeyu Zheng, Junhyuk Oh, Satinder Singh
In this paper we build on the Optimal Rewards Framework of Singh et al. [2010] that defines the optimal intrinsic reward function as one that when used by an RL agent achieves behavior that optimizes the
From Stochastic Planning to Marginal MAP
Hao(Jackson) Cui, Radu Marinescu, Roni Khardon
Neural Information Processing Systems http://nips.cc/
Optimization of Smooth Functions with Noisy Observations: Local Minimax Rates
Yining Wang, Sivaraman Balakrishnan, Aarti Singh
Neural Information Processing Systems http://nips.cc/
Automatic Program Synthesis of Long Programs with a Learned Garbage Collector
We train a neural network to map from the current state and the outputs to the program's next statement.
Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies
Sungryull Sohn, Junhyuk Oh, Honglak Lee
To further motivate the problem, let's consider a scenario in which an agent needs to generalize to a complex novel task by performing a composition of subtasks where the task description and
Speculative Monte-Carlo Tree Search
Monte-Carlo tree search (MCTS) is an influential sequential decision-making algorithm notably employed in AlphaZero.
Discretely Beyond 1 /e: Guided Combinatorial Algorithms for Submodular Maximization
These are achieved by guiding the randomized greedy algorithm with a fast local search algorithm. Further, we develop deterministic versions of these algorithms, maintaining the same ratio and asymptotic time complexity.