Reinforcement Learning
Distributional Policy Optimization: An Alternative Approach for Continuous Control
Chen Tessler, Guy Tennenholtz, Shie Mannor
Wesuggestanoveldistributional framework, able to represent arbitrary distribution functions over the continuous actionspace.
ContrastiveLearningasGoal-Conditioned ReinforcementLearning
We usethisideatoreinterpret aprior RLmethod asperforming contrastivelearning, and then use the idea to propose a much simpler method that achieves similar performance. Across arange ofgoal-conditioned RLtasks, wedemonstrate that contrastive RL methods achieve higher success rates than prior non-contrastive methods, including in the offline RL setting.
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
In such cases, using a set of expert trajectories could help to learn faster.
