A list of papers regarding generalization in (deep) reinforcement learning. Please feel free to open an issue to add papers.
- [ICLR 2023] Investigating Multi-Task Pretraining and Generalization in Reinforcement Learning
- [ICLR 2023] Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories
- [ICLR 2023] Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes
- [ICLR 2023] Powderworld: A Platform for Understanding Generalization via Rich Task Distributions
- [ICLR 2023] BC-IRL: Learning Generalizable Reward Functions from Demonstrations
- [ICLR 2023] Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning
- [ICLR 2023] When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning
- [ICLR 2023] RPM: Generalizable Multi-Agent Policies for Multi-Agent Reinforcement Learning
- [ICLR 2023] MANISKILL2: A UNIFIED BENCHMARK FOR GENERALIZABLE MANIPULATION SKILLS
- [ICML2023] Model-agnostic Measure of Generalization Difficulty
- [ICML2023] On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness
- [ICML2023] The Benefits of Model-Based Generalization in Reinforcement Learning
- [NeurIPS 2022] Rethinking Value Function Learning for Generalization in Reinforcement Learning
- [NeurIPS 2022] Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning
- [NeurIPS 2022] Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions
- [OpenReview 2022] Adversarial Style Transfer for Robust Policy Optimization in Reinforcement Learning
- [ECCV 2022] Style-Agnostic Reinforcement Learning
- [ICML 2022] Improving Policy Optimization with Generalist-Specialist Learning
- [ICML 2022] Learning Dynamics and Generalization in Reinforcement Learning
- [ICML 2022] Recurrent Model-Free RL is a Strong Baseline for Many POMDPs
- [ICML 2022] DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck
- [ICLRW 2022] A Study of Off-Policy Learning in Environments with Procedural Content Generation
- [ICLR 2022] Local Feature Swapping for Generalization in Reinforcement Learning
- [ICLR 2022] Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL
- [arXiv 2021] A Survey of Generalisation in Deep Reinforcement Learning
- [arXiv 2021] Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation
- [arXiv 2021] Sparse Attention Guided Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learning
- [NeurIPS 2021] Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability
- [NeurIPS 2021] Automatic Data Augmentation for Generalization in Reinforcement Learning
- [ICML 2021] Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment
- [ICML 2021] Decoupling Value and Policy for Generalization in Reinforcement Learning
- [ICML 2021] Prioritized Level Replay
- [ICRA 2021] Generalization in Reinforcement Learning by Soft Data Augmentation
- [ICLR 2021] Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning
- [ICLR 2021] Transient Non-stationarity and Generalisation in Deep Reinforcement Learning
- [ICLR 2021] Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
- [Procgen Challenge 2020] Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks
- [NeurIPS 2020] Instance based Generalization in Reinforcement Learning
- [NeurIPS 2020] Improving Generalization in Reinforcement Learning with Mixture Regularization
- [NeurIPS 2020] Reinforcement Learning with Augmented Data
- [ICML 2020] Fast Adaptation to New Environments via Policy-Dynamics Value Functions
- [ICML 2020] Leveraging Procedural Generation to Benchmark Reinforcement Learning
- [ICLR 2020] Observational Overfitting in Reinforcement Learning
- [ICLR 2020] Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning
- [NeurIPS 2019] Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
- [ICML 2019] On the Generalization Gap in Reparameterizable Reinforcement Learning
- [ICML 2019] Quantifying Generalization in Reinforcement Learning
- [ICML 2019] Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation
- [ICMLW 2019] The Principle of Unchanged Optimality in Reinforcement Learning Generalization
- [arXiv 2018] Natural Environment Benchmarks for Reinforcement Learning
- [arXiv 2018] Assessing Generalization in Deep Reinforcement Learning
- [arXiv 2018] A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning
- [arXiv 2018] A Study on Overfitting in Deep Reinforcement Learning
- [arXiv 2018] Gotta Learn Fast: A New Benchmark for Generalization in RL
- [NeurIPSW 2018] Generalization and Regularization in DQN
- [ICRA 2018] Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
- [NeurIPS 2017] Towards Generalization and Simplicity in Continuous Control