Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research

This is experimental HTML to improve accessibility. We invite you to report rendering errors. Use Alt+Y to toggle on accessible reporting links and Alt+Shift+Y to toggle off. Learn more about this project and help improve conversions.

Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research Michał Bortkiewicz 1 Władek Pałucki 2 Vivek Myers 3 Tadeusz Dziarmaga 4 Tomasz Arczewski 4 Łukasz Kuciński 2,5,6 Benjamin Eysenbach 7 1 Warsaw University of Technology 2 University of Warsaw 3 UC Berkeley 4 Jagiellonian University 5 Polish Academy of Sciences 6 IDEAS NCBR 7 Princeton University michalbortkiewicz8@gmail.com wladek.palucki@gmail.com Abstract Self-supervision has the potential to transform reinforcement learning (RL), paralleling the breakthroughs it has enabled in other areas of machine learning. While

related reading

• Contrastive Learning as Goal-Conditioned Reinforcement Learningarxiv.org
• Reinforcement Learning in Newcomblike Problemsproceedings.neurips.cc
• [2103.06326] S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learningarxiv.org
• [1707.06347] Proximal Policy Optimization Algorithmsarxiv.org
• [1709.06560] Deep Reinforcement Learning that Mattersarxiv.org
• Reinforcement Learning via Implicit Imitation Guidancearxiv.org
• Decoupling Representation Learning from Reinforcement Learningarxiv.org
• 1011.0686arxiv.org
• Exploration for the Efficient Deployment of Reinforcement Learning Agentsopenreview.net
• [2602.11399] Can We Really Learn One Representation to Optimize All Rewards?arxiv.org
• Enhancing Offline Reinforcement Learning with Curriculum Learning-Based Trajectory Valuationarxiv.org
• 2006.10742arxiv.org