NeurIPS 2024 accepted papers on Reinforcement learning
271 of the 4,560 papers accepted at NeurIPS 2024 (5.9%) are on Reinforcement learning, compared with 7.6% at NeurIPS 2023. They fall into 6 topics.
See NeurIPS 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Visual and representation RL · 91 papers
- DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning (15 citations)
- A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data (12 citations)
- A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning (7 citations)
- SCaR: Refining Skill Chaining for Long-Horizon Robotic Manipulation via Dual Regularization (7 citations)
- Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement (6 citations)
- PUZZLES: A Benchmark for Neural Algorithmic Reasoning (6 citations)
- Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning (6 citations)
- Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents (5 citations)
- Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer (5 citations)
- Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning (4 citations)
- Efficient Multi-task Reinforcement Learning with Cross-Task Policy Guidance (4 citations)
- Model-Based Transfer Learning for Contextual Reinforcement Learning (4 citations)
and 79 more in the interactive map.
Policy gradient and actor-critic · 51 papers
- Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization (17 citations)
- Diffusion Actor-Critic with Entropy Regulator (10 citations)
- Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning (5 citations)
- Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking (4 citations)
- Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps (3 citations)
- DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning (3 citations)
- Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient (3 citations)
- Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation (2 citations)
- An Analytical Study of Utility Functions in Multi-Objective Reinforcement Learning (2 citations)
- Distributional Reinforcement Learning with Regularized Wasserstein Loss (2 citations)
- Dual Critic Reinforcement Learning under Partial Observability (2 citations)
- Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn (2 citations)
and 39 more in the interactive map.
MDPs and planning · 46 papers
- Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL (11 citations)
- Provable Partially Observable Reinforcement Learning with Privileged Information (4 citations)
- Contextual Bilevel Reinforcement Learning for Incentive Alignment (2 citations)
- Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes (2 citations)
- Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP Iteration (2 citations)
- Flipping-based Policy for Chance-Constrained Markov Decision Processes (2 citations)
- Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy (2 citations)
- A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation (1 citation)
- Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms (1 citation)
- Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning (1 citation)
- Finding good policies in average-reward Markov Decision Processes without prior knowledge (1 citation)
- Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation (1 citation)
and 34 more in the interactive map.
Offline RL · 39 papers
- Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning (7 citations)
- Diffusion Policies Creating a Trust Region for Offline Reinforcement Learning (6 citations)
- Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL (5 citations)
- Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL (4 citations)
- Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning (4 citations)
- Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning? (4 citations)
- Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression (4 citations)
- Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning (3 citations)
- Iteratively Refined Behavior Regularization for Offline Reinforcement Learning (3 citations)
- Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model (3 citations)
- Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions (3 citations)
- A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective (2 citations)
and 27 more in the interactive map.
Imitation learning · 23 papers
- BAKU: An Efficient Transformer for Multi-Task Policy Learning (17 citations)
- Vision-Language Navigation with Energy-Based Policy (11 citations)
- Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning (10 citations)
- SurgicAI: A Hierarchical Platform for Fine-Grained Surgical Policy Learning and Benchmarking (4 citations)
- C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory (3 citations)
- In-Trajectory Inverse Reinforcement Learning: Learn Incrementally Before an Ongoing Trajectory Terminates (3 citations)
- SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning (3 citations)
- Causal Imitation for Markov Decision Processes: a Partial Identification Approach (2 citations)
- DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control (2 citations)
- Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models (2 citations)
- Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control (2 citations)
- Mitigating Covariate Shift in Behavioral Cloning via Robust Stationary Distribution Correction (2 citations)
and 11 more in the interactive map.
RL from feedback · 21 papers
- Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning (10 citations)
- Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms (7 citations)
- Adaptive Preference Scaling for Reinforcement Learning with Human Feedback (4 citations)
- Online Iterative Reinforcement Learning from Human Feedback with General Preference Model (4 citations)
- Multi-turn Reinforcement Learning with Preference Human Feedback (3 citations)
- Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control (2 citations)
- One-Shot Safety Alignment for Large Language Models via Optimal Dualization (2 citations)
- REBEL: Reinforcement Learning via Regressing Relative Rewards (2 citations)
- Stepwise Alignment for Constrained Language Model Policy Optimization (2 citations)
- Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment (1 citation)
- GUIDE: Real-Time Human-Shaped Agents (1 citation)
- Imitating Language via Scalable Inverse Reinforcement Learning (1 citation)
and 9 more in the interactive map.