Search Results for author:
Found 6 papers, 2 papers with code
From Past to Future: Rethinking Eligibility Traces
In this paper, we introduce a fresh perspective on the challenges of credit assignment and policy evaluation.
Coagent Networks: Generalized and Scaled
However, the coagent framework is not just an alternative to BDL; the two approaches can be blended: BDL can be combined with coagent learning rules to create architectures with the advantages of both approaches.
Robust Markov Decision Processes without Model Estimation
Moreover, we prove the alternative form still plays a similar role as the original form.
Towards Safe Policy Improvement for Non-Stationary MDPs
Many real-world sequential decision-making problems involve critical systems with financial risks and human-life risks.
Evaluating the Performance of Reinforcement Learning Algorithms
Performance evaluations are critical for quantifying algorithmic advances in reinforcement learning.
Classical Policy Gradient: Preserving Bellman's Principle of Optimality
We propose a new objective function for finite-horizon episodic Markov decision processes that better captures Bellman's principle of optimality, and provide an expression for the gradient of the objective.
