Search Results for author:
Found 5 papers, 4 papers with code
Long-Term Planning and Situational Awareness in OpenAI Five
Understanding how knowledge about the world is represented within model-free deep reinforcement learning methods is a major challenge given the black box nature of its learning process within high-dimensional observation and action spaces.
Dota 2 with Large Scale Deep Reinforcement Learning
On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game.
Evolved Policy Gradients
We propose a metalearning approach for learning gradient-based reinforcement learning (RL) algorithms.
Proximal Policy Optimization Algorithms
We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.
Hindsight Experience Replay
Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL).
