Reinforcement Learning
Generalized Hindsight for Reinforcement Learning
Intuitively, given a behavior generated under one task, Generalized Hindsight returns a different task that the behavior is better suited for. Then, the behavior is relabeled with this new task before being used by an off-policy RL optimizer.
Towards Robust Bisimulation Metric Learning
Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and informativeness to the policy.
Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Gradient Estimators for Reinforcement Learning
Gregory Farquhar, Shimon Whiteson, Jakob Foerster
Neural Information Processing Systems http://nips.cc/
Learning from Trajectories via Subgoal Discovery
Sujoy Paul, Jeroen Vanbaar, Amit Roy-Chowdhury
Neural Information Processing Systems http://nips.cc/
Automatic Curriculum Learning through Value Disagreement
Continually solving new, unsolved tasks is the key to learning diverse behaviors. Through reinforcement learning (RL), we have made massive strides towards solving tasks that have a single goal.
