mazoure20a.pdf

N/A

Leveraging exploration in off-policy algorithms via normalizing flows Bogdan Mazoure∗ 1,2 , Thang Doan* 1,2 , Audrey Durand2,3 , Joelle Pineau1,2,4 , R Devon Hjelm2,5,6 1 2 3 McGill University Mila – Quebec AI Institute Université Laval 4 5 Facebook AI Research Microsoft Research Montreal 6…

saved by

• Akira Yoshiyama

related reading

• [2506.22401] Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RLarxiv.org
• [2602.05999] On the Role of Computation in Reinforcement Learningarxiv.org
• [2606.05555] Representation Learning Enables Scalable Multitask Deep Reinforcement Learningarxiv.org
• [2602.11399] Can We Really Learn One Representation to Optimize All Rewards?arxiv.org
• RL_Notes__final_.pdfjubayer-ibn-hamid.github.io
• [1709.06560] Deep Reinforcement Learning that Mattersarxiv.org
• 1011.0686arxiv.org
• [1707.06347] Proximal Policy Optimization Algorithmsarxiv.org
• Flow Matching Policy Gradientsflowreinforce.github.io
• Soft Actor-Critic - Spinning Up documentationspinningup.openai.com
• Exploration for the Efficient Deployment of Reinforcement Learning Agentsopenreview.net
• Reinforcement Learning in Newcomblike Problemsproceedings.neurips.cc