Researchers suggest AI can learn common sense from animals

AI researchers developing reinforcement learning agents could learn a lot from animals. That’s according to recent analysis by Google’s DeepMind, Imperial College London, and University of Cambridge researchers assessing AI and non-human animals.

Read More

AI researchers challenge a robot to ride a skateboard in simulation

AI researchers say they’ve created a framework for controlling four-legged robots. To demonstrate the robust nature of the framework, AI researchers made the system slip on frictionless surfaces to mimic a banana peel, ride a skateboard, and climb on a bridge while walking on a treadmill.

Read More

Tackling Open Challenges in Offline Reinforcement Learning

Over the past several years, there has been a surge of interest in reinforcement learning (RL) driven by its high-profile successes in game playing and robotic control. However, unlike supervised learning methods, which learn from massive datasets that are collected once and then reused, RL algorithms use a trial-and-error feedback loop that requires active interaction during learning, collecting data every time a new policy is learned.

Read More

Facebook develops AI algorithm that learns to play poker on the fly

Facebook develops AI algorithm that learns to play poker on the fly

Facebook researchers have developed a general AI framework called Recursive Belief-based Learning (ReBeL) that they say achieves better-than-human performance in heads-up, no-limit Texas hold’em poker while using less domain knowledge than any prior poker AI.

Read More

Why does the optimal policy exist?

In a finite Markov Decision Process (MDP), the optimal policy is defined as a policy that maximizes the value of all states at the same time¹. In other words, if an optimal policy exists, then the policy that maximizes the value of state s is the same as the policy that maximizes the value of state s’.² But why should such a policy exist?

Read More

List of inverse Reinforcement Learning (IRL) papers

inverse Reinforcement Learning (IRL) papers

Inverse Reinforcement Learning papers: A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models. (IRL, Algorithms, Apprenticeship Learning, Maximum Margin Planning, Maximum Entropy, Nonlinear with Gaussian Processes, Generative Adversarial Imitation Learning).

Read More
1 2