Search Results for author:
Found 6 papers, 3 papers with code
Explicit Gradient Learning for Black-Box Optimization
We prove the convergence of EGL to a stationary point and its robustness in the optimization of integrable functions.
A Coupled Flow Approach to Imitation Learning
In reinforcement learning and imitation learning, an object of central importance is the state distribution induced by the policy.
Recomposing the Reinforcement Learning Building Blocks with Hypernetworks
In particular, the input of the Q-function is both the state and the action, and in multi-task problems (Meta-RL) the policy can take a state and a context.
Explicit Gradient Learning
Instead of fitting the function, EGL trains a NN to estimate the objective gradient directly.
Safe Policy Learning from Observations
The primary advantages of our approach, termed Rerouted Behavior Improvement (RBI), over other safe learning methods are its stability in the presence of value estimation errors and the elimination of a policy search process.
Constrained Policy Improvement for Safe and Efficient Reinforcement Learning
To minimize the improvement penalty, the RBI idea is to attenuate rapid policy changes of low probability actions which were less frequently sampled.
