Reinforcement learning (RL) is a machine learning approach that trains agents to maximize
cumulative rewards through interactions with environments. The integration of RL with deep …

Reinforcement learning is about learning agent models that make the best sequential
decisions in unknown environments. In an unknown environment, the agent needs to …

In this paper, we analyze several methods for approximating gradients of noisy functions
using only function values. These methods include finite differences, linear interpolation …

Exploration is a key problem in reinforcement learning, since agents can only learn from
data they acquire in the environment. With that in mind, maintaining a population of agents is …

Sim-to-real transfer is a powerful paradigm for robotic reinforcement learning. The ability to
train policies in simulation enables safe exploration and large-scale data collection quickly …

A major component of overfitting in model-free reinforcement learning (RL) involves the case
where the agent may mistakenly correlate reward with certain spurious features from the …

Trajectory optimizers for model-based reinforcement learning, such as the Cross-Entropy
Method (CEM), can yield compelling results even in high-dimensional control tasks and …

We introduce ES-MAML, a new framework for solving the model agnostic meta learning
(MAML) problem based on Evolution Strategies (ES). Existing algorithms for MAML are …

Deep reinforcement learning (DRL) and evolution strategies (ESs) have surpassed human-
level control in many sequential decision-making problems, yet many open challenges still …

In this paper, we propose and analyze zeroth-order stochastic approximation algorithms for
nonconvex and convex optimization, with a focus on addressing constrained optimization …