Benjamin Eysenbach
Princeton University · 101 works · 1,022 citations · h-index 17
Top works
- Clustervision: Visual Supervision of Unsupervised Clustering
- Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning
- Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings
- Diversity is All You Need: Learning Skills without a Reward Function
- ViNG: Learning Open-World Navigation with Visual Goals
- Efficient Exploration via State Marginal Matching
- Contrastive Learning as Goal-Conditioned Reinforcement Learning
- Unsupervised Meta-Learning for Reinforcement Learning
- Search on the Replay Buffer: Bridging Planning and Reinforcement Learning
- Learning to Reach Goals via Iterated Supervised Learning
- Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement
- Model-Based Visual Planning with Self-Supervised Functional Distances
- Learning to be Safe: Deep RL with a Safety Critic
- Learning To Reach Goals Without Reinforcement Learning
- If MaxEnt RL is the Answer, What is the Question?
- Unsupervised Curricula for Visual Meta-Reinforcement Learning
- Rapid Exploration for Open-World Navigation with Latent Goal Models
- HIQL: Offline Goal-Conditioned RL with Latent States as Actions
- Maximum Entropy RL (Provably) Solves Some Robust RL Problems
- Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs