SysCon reinforcement learning reading group

A weekly reinforcement learning reading group. We take turns picking a paper to read each week, which we then discuss together. Each session is 1h. Sessions are typically on Fridays, in room 103253.

We also communicate in #reading_rl channel on the SysCon slack.

Contact person: Ruoqi Zhang.

Paper List 2023

Week	Paper	Venue	Available Code
24	Efficient Deep Reinforcement Learning Requires Regulating Overfitting	ICLR 2023
22	Planning with Diffusion for Flexible Behavior Synthesis	ICML 2022
21	Explainable Reinforcement Learning through a Causal Lens	AAAI 2020
19	EDGI: EQUIVARIANT DIFFUSION FOR PLANNING WITH EMBODIED AGENTS	ICLR 2023 workshop RRL
18	DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning	Neurips 2022	Official Code
17	Safe Reinforcement Learning With Stability Guarantee for Motion Planning of Autonomous Vehicles	IEEE 2021
15	Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting	IEEE 2012
14	Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning	Annual Review 2022
12	When to Update Your Model: Constrained Model-based Reinforcement Learning	NeurIPS 2022
10	Neural Dynamic Policies for End-to-End Sensorimotor Learning	Neurips 2020	Official Code
8	Risk-Averse Bayes-Adaptive Reinforcement Learning	NeurIPS 2021
7	Learning Latent Dynamics for Planning from Pixels	ICML 2019	Official Code
5	Mastering Diverse Domains through World Models	Arxiv 2023	Official Code
4	Curiosity in Hindsight	Neurips 2022
3	Proximal Policy Optimization Algorithms	Arxiv 2017	Stable Baselines 3
2	Model-Predictive Planning via Cross-Entropy and Gradient-Based Optimization	L4DC 2020	Official Code
1	Decision Transformer: Reinforcement Learning via Sequence Modeling	NeurIPS 2021	Official Code

Paper List 2022

Week	Paper	Venue	Available Code
51	Temporal Difference Learning for Model Predictive Control	ICML 2022	Official Code
50	Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor	ICML 2018	Official Code
49	Reinforcement Learning with Deep Energy-Based Policies	PMLR 2017	Official Code
48	Conservative Q-Learning for Offline Reinforcement Learning	NeurIPS 2020	Official Code