Reinforcement Learning
Search on the Replay Buffer: Bridging Planning and Reinforcement Learning
Ben Eysenbach, Russ R. Salakhutdinov, Sergey Levine
The history of learning for control has been an exciting back and forth between two broad classes of algorithms: planning and reinforcement learning.
Imitation-Projected Programmatic Reinforcement Learning
Abhinav Verma, Hoang Le, Yisong Yue, Swarat Chaudhuri
However, such a distillation process can yield a highly suboptimal programmatic policy -- i.e., a large
Neurosymbolic Reinforcement Learning with Formally Verified Exploration Greg Anderson UT Austin
So far, these methods have only been used to discover policies over simple, finite action spaces.
Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning
It also does not enjoy SNIS's inherent stability and boundedness.
Reinforcement Learning with General Value Function Approximation: Provably Efficient Approach via Bounded Eluder Dimension
In reinforcement learning (RL), we study how an agent maximizes the cumulative reward by interacting with an unknown environment. RL finds enormous applications in a wide variety of domains, e.g., robotics [
VIREL: A Variational Inference Framework for Reinforcement Learning
Matthew Fellows, Anuj Mahajan, Tim G. J. Rudner, Shimon Whiteson
Applying probabilistic models to reinforcement learning (RL) enables the uses of powerful optimisation tools such as variational inference in RL.
Exploration via Hindsight Goal Generation
However, the sparsity of such reward definition makes traditional reinforcement learning algorithms very inefficient.
43207fd5e34f87c48d584fc5c11befb8-Paper.pdf
It is well believed that model-based RL, where the agent learns the model of the environment and then performs planning in the model, is significantly more sample efficient than model-free RL. Recent empirical advances also justify such a belief (e.g.