What happens when something is optimised hard against a learned scorer, and when that stops being a theoretical worry.
Tag: reinforcement learning
From Reinforcement Learning to Deep Reinforcement Learning
Reinforcement learning boasts a substantial history predating the recent surge in deep learning. Reinforcement learning is learning what to do—how … More
gym-minigrid online manual control
To implement agents that can learn through social interaction as humans do, I decided to explore how humans instruct each … More
Counterfactually-Guided Policy Search
A compelling way to reduce the cost of real experience in reinforcement learning is to learn policies on data synthesised … More
Inverse Reinforcement Learning from a Gradient-based Learner
While searching for gradient based approaches in Inverse Reinforcement Learning, I came across the recent contribution of Ramponi et al. … More
Bayesian Inverse Reinforcement Learning
In the last couple of months I have been studying Inverse Reinforcement Learning approaches, in particular the work of Ramachandran … More
Learning with Opponent-Learning Awareness
Learning with Opponent-Learning Awareness (LOLA), introduced by Foerster et al. in 2018, has each agent take into account the anticipated … More
Policy Gradient Methods for Reinforcement Learning
Considering Actor-Critic for handling the decision making of agents, my colleague and I started an interesting discussion about policy gradient … More
