ICML 2024 accepted papers on Reinforcement learning

228 of the 2,610 papers accepted at ICML 2024 (8.7%) are on Reinforcement learning, compared with 10.2% at ICML 2023. They fall into 6 topics.

See ICML 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 · 68 papers

Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning (4 citations)
Rethinking Decision Transformer via Hierarchical Reinforcement Learning (4 citations)
Exploration and Anti-Exploration with Distributional Random Network Distillation (3 citations)
Mixtures of Experts Unlock Parameter Scaling for Deep RL (3 citations)
Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts (2 citations)
Chain-of-Thought Predictive Control (2 citations)
Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning (2 citations)
End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations (2 citations)
Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning (2 citations)
Code as Reward: Empowering Reinforcement Learning with VLMs (1 citation)
Cross-Domain Policy Adaptation by Capturing Representation Mismatch (1 citation)
HarmonyDream: Task Harmonization Inside World Models (1 citation)

and 56 more in the interactive map.

Policy gradient and actor-critic · 59 papers

Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning (3 citations)
Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic (3 citations)
Stop Regressing: Training Value Functions via Classification for Scalable Deep RL (3 citations)
ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization (2 citations)
ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages (2 citations)
Trust the Model Where It Trusts Itself - Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption (2 citations)
Bayesian Exploration Networks (1 citation)
Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation (1 citation)
Distributional Bellman Operators over Mean Embeddings (1 citation)
Neural-Kernel Conditional Mean Embeddings (1 citation)
Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation (1 citation)
Single-Trajectory Distributionally Robust Reinforcement Learning (1 citation)

and 47 more in the interactive map.

Offline RL · 29 papers

and 17 more in the interactive map.

MDPs and planning · 28 papers

and 16 more in the interactive map.

RL from feedback · 26 papers

RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback (6 citations)
Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data (4 citations)
A Minimaximalist Approach to Reinforcement Learning from Human Feedback (3 citations)
WARM: On the Benefits of Weight Averaged Reward Models (3 citations)
ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL (2 citations)
Controlled Decoding from Language Models (2 citations)
Dense Reward for Free in Reinforcement Learning from Human Feedback (2 citations)
Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem (2 citations)
Human Alignment of Large Language Models through Online Preference Optimisation (2 citations)
Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning (2 citations)
Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization (1 citation)
Feedback Efficient Online Fine-Tuning of Diffusion Models (1 citation)

and 14 more in the interactive map.

Imitation learning · 18 papers

and 6 more in the interactive map.