Workshop
Generalization in Planning (GenPlan '23)
Pulkit Verma 路 Siddharth Srivastava 路 Aviv Tamar 路 Felipe Trevizan
Room 238 - 239
Sat 16 Dec, 6:15 a.m. PST
This workshop aims to bridge highly active but largely parallel research communities, addressing the problem of generalizable and transferrable learning for all forms of sequential decision making (SDM), including reinforcement learning and AI planning. We expect that this workshop will play a key role in accelerating the speed of foundational innovation in SDM with a synthesis of the best ideas for learning generalizable representations of learned knowledge and for reliably utilizing the learned knowledge across different sequential decision-making problems. NeurIPS presents an ideal, inclusive venue for dialog and technical interaction among researchers spanning the vast range of research communities that focus on these topics.
Schedule
Sat 6:15 a.m. - 6:20 a.m.
|
Opening Remarks
(
Remarks
)
>
SlidesLive Video |
馃敆 |
Sat 6:20 a.m. - 6:55 a.m.
|
Causal Dynamics Learning for Task-Independent State Abstraction
(
Invited Talk
)
>
SlidesLive Video |
Peter Stone 馃敆 |
Sat 6:55 a.m. - 7:05 a.m.
|
Learning Abstract World Models for Value-preserving Planning with Options
(
Contributed Talk
)
>
link
SlidesLive Video |
Rafael Rodriguez Sanchez 路 George Konidaris 馃敆 |
Sat 7:05 a.m. - 7:15 a.m.
|
Reinforcement Learning with Augmentation Invariant Representation: A Non-contrastive Approach
(
Contributed Talk
)
>
link
SlidesLive Video |
Nasik Muhammad Nafi 路 William Hsu 馃敆 |
Sat 7:15 a.m. - 7:25 a.m.
|
Explore to Generalize in Zero-Shot RL
(
Contributed Talk
)
>
link
SlidesLive Video |
Ev Zisselman 路 Itai Lavie 路 Daniel Soudry 路 Aviv Tamar 馃敆 |
Sat 7:25 a.m. - 8:00 a.m.
|
Value-Based Abstractions for Planning
(
Invited Talk
)
>
SlidesLive Video |
Amy Zhang 馃敆 |
Sat 8:00 a.m. - 8:30 a.m.
|
Coffee Break
(
Coffee Break
)
>
|
馃敆 |
Sat 8:30 a.m. - 9:05 a.m.
|
Learning General Policies and Sketches
(
Invited Talk
)
>
SlidesLive Video |
Hector Geffner 馃敆 |
Sat 9:05 a.m. - 9:15 a.m.
|
GOOSE: Learning Domain-Independent Heuristics
(
Contributed Talk
)
>
link
SlidesLive Video |
Dillon Chen 路 Felipe Trevizan 路 Sylvie Thiebaux 馃敆 |
Sat 9:15 a.m. - 9:25 a.m.
|
Hierarchical Reinforcement Learning with AI Planning Models
(
Contributed Talk
)
>
link
SlidesLive Video |
Junkyu Lee 路 Michael Katz 路 Don Joven Agravante 路 Miao Liu 路 Geraud Nangue Tasse 路 Tim Klinger 路 Shirin Sohrabi Araghi 馃敆 |
Sat 9:25 a.m. - 9:35 a.m.
|
Epistemic Exploration for Generalizable Planning and Learning in Non-Stationary Stochastic Settings
(
Contributed Talk
)
>
link
SlidesLive Video |
Rushang Karia 路 Pulkit Verma 路 Gaurav Vipat 路 Siddharth Srivastava 馃敆 |
Sat 9:35 a.m. - 9:45 a.m.
|
POMRL: No-Regret Learning-to-Plan with Increasing Horizons
(
Contributed Talk
)
>
link
SlidesLive Video |
Khimya Khetarpal 路 Claire Vernade 路 Brendan O'Donoghue 路 Satinder Singh 路 Tom Zahavy 馃敆 |
Sat 9:45 a.m. - 9:55 a.m.
|
A Theoretical Explanation of Deep RL Performance in Stochastic Environments
(
Contributed Talk
)
>
link
SlidesLive Video |
Cassidy Laidlaw 路 Banghua Zhu 路 Stuart J Russell 路 Anca Dragan 馃敆 |
Sat 9:55 a.m. - 11:30 a.m.
|
Lunch Break
(
Lunch Break
)
>
|
馃敆 |
Sat 11:30 a.m. - 12:05 p.m.
|
Logic, Automata, and Games in Linear Temporal Logics on Finite Traces
(
Invited Talk
)
>
SlidesLive Video |
Giuseppe De Giacomo 馃敆 |
Sat 12:05 p.m. - 12:15 p.m.
|
Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines
(
Contributed Talk
)
>
link
SlidesLive Video |
Yu-An Lin 路 Chen-Tao Lee 路 Guan-Ting Liu 路 Pu-Jen Cheng 路 Shao-Hua Sun 馃敆 |
Sat 12:15 p.m. - 12:25 p.m.
|
PADDLE: Logic Program Guided Policy Reuse in Deep Reinforcement Learning
(
Contributed Talk
)
>
link
SlidesLive Video |
Hao Zhang 路 Tianpei Yang 路 YAN ZHENG 路 Jianye Hao 路 Matthew Taylor 馃敆 |
Sat 12:25 p.m. - 1:00 p.m.
|
Poster Session 1
(
Poster Session
)
>
|
馃敆 |
Sat 1:00 p.m. - 1:30 p.m.
|
Coffee Break
(
Coffee Break
)
>
|
馃敆 |
Sat 1:30 p.m. - 2:00 p.m.
|
Poster Session 2
(
Poster Session
)
>
|
馃敆 |
Sat 2:00 p.m. - 2:35 p.m.
|
In-Context Learning of Sequential Decision-Making Tasks
(
Invited Talk
)
>
SlidesLive Video |
Roberta Raileanu 馃敆 |
Sat 2:35 p.m. - 2:45 p.m.
|
RL3: Boosting Meta Reinforcement Learning via RL inside RL2
(
Contributed Talk
)
>
link
SlidesLive Video |
Abhinav Bhatia 路 Samer Nashed 路 Shlomo Zilberstein 馃敆 |
Sat 2:45 p.m. - 2:55 p.m.
|
Towards General-Purpose In-Context Learning Agents
(
Contributed Talk
)
>
link
SlidesLive Video |
Louis Kirsch 路 James Harrison 路 Daniel Freeman 路 Jascha Sohl-Dickstein 路 J眉rgen Schmidhuber 馃敆 |
Sat 2:55 p.m. - 3:25 p.m.
|
Panel Discussion
(
Panel
)
>
link
SlidesLive Video |
馃敆 |
Sat 3:25 p.m. - 3:30 p.m.
|
Closing Remarks
(
Remarks
)
>
SlidesLive Video |
馃敆 |
-
|
Massively Scalable Inverse Reinforcement Learning for Route Optimization ( Poster ) > link | Matt Barnes 路 Matthew Abueg 路 Oliver Lange 路 Matt Deeds 路 Jason Trader 路 Denali Molitor 路 Markus Wulfmeier 路 Shawn O'Banion 馃敆 |
-
|
Reasoning with Language Model is Planning with World Model ( Poster ) > link | Shibo Hao 路 Yi Gu 路 Haodi Ma 路 Joshua Hong 路 Zhen Wang 路 Daisy Zhe Wang 路 Zhiting Hu 馃敆 |
-
|
Robustness and Regularization in Reinforcement Learning ( Poster ) > link | Esther Derman 路 Yevgeniy Men 路 Matthieu Geist 路 Shie Mannor 馃敆 |
-
|
Learning Generalizable Visual Task Through Interaction ( Poster ) > link | Weiwei Gu 路 Anant Sah 路 Nakul Gopalan 馃敆 |
-
|
Non-adaptive Online Finetuning for Offline Reinforcement Learning ( Poster ) > link | Audrey Huang 路 Mohammad Ghavamzadeh 路 Nan Jiang 路 Marek Petrik 馃敆 |
-
|
Learning Interactive Real-World Simulators ( Poster ) > link | Sherry Yang 路 Yilun Du 路 Kamyar Ghasemipour 路 Jonathan Tompson 路 Dale Schuurmans 路 Pieter Abbeel 馃敆 |
-
|
Agent-Centric State Discovery for Finite-Memory POMDPs ( Poster ) > link | Lili Wu 路 Ben Evans 路 Riashat Islam 路 Raihan Seraj 路 Yonathan Efroni 路 Alex Lamb 馃敆 |
-
|
Simple Data Sharing for Multi-Tasked Goal-Oriented Problems ( Poster ) > link | Ying Fan 路 Jingling Li 路 Adith Swaminathan 路 Aditya Modi 路 Ching-An Cheng 馃敆 |
-
|
Leveraging Behavioral Cloning for Representation Alignment in Cross-Domain Policy Transfer ( Poster ) > link | Hayato Watahiki 路 Ryo Iwase 路 Ryosuke Unno 路 Yoshimasa Tsuruoka 馃敆 |
-
|
Understanding Representations Pretrained with Auxiliary Losses for Embodied Agent Planning ( Poster ) > link | Yuxuan (Effie) Li 路 Luca Weihs 馃敆 |
-
|
Contrastive Abstraction for Reinforcement Learning ( Poster ) > link | Vihang Patil 路 Markus Hofmarcher 路 Elisabeth Rumetshofer 路 Sepp Hochreiter 馃敆 |
-
|
Work-in-Progress: Using Symbolic Planning with Deep RL to Improve Learning ( Poster ) > link | Tianpei Yang 路 Srijita Das 路 Christabel Wayllace 路 Matthew Taylor 馃敆 |
-
|
Graph Neural Networks and Graph Kernels For Learning Heuristics: Is there a difference? ( Poster ) > link | Dillon Chen 路 Felipe Trevizan 路 Sylvie Thiebaux 馃敆 |
-
|
Learning How to Create Generalizable Hierarchies for Robot Planning ( Poster ) > link | Naman Shah 路 Siddharth Srivastava 馃敆 |
-
|
Plansformer: Generating Symbolic Plans using Transformers ( Poster ) > link | Vishal Pallagani 路 Bharath Muppasani 路 Keerthiram Murugesan 路 Francesca Rossi 路 Lior Horesh 路 Biplav Srivastava 路 Francesco Fabiano 路 Andrea Loreggia 馃敆 |
-
|
Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learning ( Poster ) > link | Lukas Sch盲fer 路 Filippos Christianos 路 Amos Storkey 路 Stefano Albrecht 馃敆 |
-
|
Towards More Likely Models for AI Planning ( Poster ) > link | Turgay Caglar 路 Sirine Belhaj 路 Tathagata Chakraborti 路 Michael Katz 路 Sarath Sreedharan 馃敆 |
-
|
Learning AI-System Capabilities under Stochasticity ( Poster ) > link | Pulkit Verma 路 Rushang Karia 路 Gaurav Vipat 路 Anmol Gupta 路 Siddharth Srivastava 馃敆 |
-
|
Contextual Pre-Planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning ( Poster ) > link | Guy Azran 路 Mohamad Hosein Danesh 路 Stefano Albrecht 路 Sarah Keren 馃敆 |
-
|
Exploiting Contextual Structure to Generate Useful Auxiliary Tasks ( Poster ) > link | Benedict Quartey 路 Ankit Shah 路 George Konidaris 馃敆 |
-
|
Normalization Enhances Generalization in Visual Reinforcement Learning ( Poster ) > link | Lu Li 路 Jiafei Lyu 路 Guozheng Ma 路 Zilin Wang 路 Zhenjie Yang 路 Xiu Li 路 Zhiheng Li 馃敆 |
-
|
Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning ( Poster ) > link | David Yunis 路 Justin Jung 路 Falcon Dai 路 Matthew Walter 馃敆 |
-
|
Contrastive Representations Make Planning Easy ( Poster ) > link | Benjamin Eysenbach 路 Vivek Myers 路 Sergey Levine 路 Russ Salakhutdinov 馃敆 |
-
|
Inverse Reinforcement Learning with Multiple Planning Horizons ( Poster ) > link | Jiayu Yao 路 Finale Doshi-Velez 路 Barbara Engelhardt 馃敆 |
-
|
Stochastic Safe Action Model Learning ( Poster ) > link | Zihao Deng 路 Brendan Juba 馃敆 |
-
|
Learning Discrete Models for Classical Planning Problems ( Poster ) > link | Forest Agostinelli 路 Misagh Soltani 馃敆 |
-
|
Multi-Agent Learning of Efficient Fulfilment and Routing Strategies in E-Commerce ( Poster ) > link | Omkar Shelke 路 Pranavi Pathakota 路 Anandsingh Chauhan 路 Hardik Meisheri 路 Harshad Khadilkar 路 Balaraman Ravindran 馃敆 |
-
|
Integrating Planning and Deep Reinforcement Learning via Automatic Induction of Task Substructures ( Poster ) > link | Jung-Chun Liu 路 Chi-Hsien Chang 路 Shao-Hua Sun 路 Tian-Li Yu 馃敆 |
-
|
Learning Generalizable Symbolic Options for Transfer in Reinforcement Learning ( Poster ) > link | Rashmeet Kaur Nayyar 路 Shivanshu Verma 路 Siddharth Srivastava 馃敆 |
-
|
Inductive Generalization in Reinforcement Learning from Specifications ( Poster ) > link | Rohit kushwah 路 Vignesh Subramanian 路 Suguman Bansal 路 Subhajit Roy 馃敆 |
-
|
MERMAIDE: Learning to Align Learners using Model-Based Meta-Learning ( Poster ) > link | Arundhati Banerjee 路 Soham Phade 路 Stefano Ermon 路 Stephan Zheng 馃敆 |
-
|
Modeling Boundedly Rational Agents with Latent Inference Budgets ( Poster ) > link | Athul Jacob 路 Abhishek Gupta 路 Jacob Andreas 馃敆 |
-
|
Mini-BEHAVIOR: A Procedurally Generated Benchmark for Long-horizon Decision-Making in Embodied AI ( Poster ) > link | Emily Jin 路 Jiaheng Hu 路 Zhuoyi Huang 路 Ruohan Zhang 路 Jiajun Wu 路 Fei-Fei Li 路 Roberto Mart铆n-Mart铆n 馃敆 |
-
|
Learning Safe Action Models with Partial Observability ( Poster ) > link | Brendan Juba 路 Hai Le 路 Ron T Stern 馃敆 |
-
|
Value Iteration with Value of Information Networks ( Poster ) > link | Samantha Johnson 路 Michael Buice 路 Koosha Khalvati 馃敆 |
-
|
Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models ( Poster ) > link | Kevin Black 路 Mitsuhiko Nakamoto 路 Pranav Atreya 路 Homer Walke 路 Chelsea Finn 路 Aviral Kumar 路 Sergey Levine 馃敆 |
-
|
COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL ( Poster ) > link | Xiyao Wang 路 Ruijie Zheng 路 Yanchao Sun 路 ruonan jia 路 Wichayaporn Wongkamjan 路 Huazhe Xu 路 Furong Huang 馃敆 |
-
|
General and Reusable Indexical Policies and Sketches ( Poster ) > link | Blai Bonet 路 Dominik Drexler 路 Hector Geffner 馃敆 |
-
|
Improving Generalization in Reinforcement Learning Training Regimes for Social Robot Navigation ( Poster ) > link | Adam Sigal 路 Hsiu-Chin Lin 路 AJung Moon 馃敆 |
-
|
Conservative World Models ( Poster ) > link | Scott Jeen 路 Tom Bewley 路 Jonathan Cullen 馃敆 |
-
|
Targeted Uncertainty Reduction in Robust MDPs ( Poster ) > link | Uri Gadot 路 Kaixin Wang 路 Esther Derman 路 Navdeep Kumar 路 Kfir Y. Levy 路 Shie Mannor 馃敆 |
-
|
Quantized Local Independence Discovery for Fine-Grained Causal Dynamics Learning in Reinforcement Learning ( Poster ) > link | Inwoo Hwang 路 Yun-hyeok Kwak 路 Suhyung Choi 路 Byoung-Tak Zhang 路 Sanghack Lee 馃敆 |
-
|
Relating Goal and Environmental Complexity for Improved Task Transfer: Initial Results ( Poster ) > link | Sunandita Patra 路 Paul Rademacher 路 Kristen Jacobson 路 Kyle Hassold 路 Onur Kulaksizoglu 路 Laura Hiatt 路 Mark Roberts 路 Dana Nau 馃敆 |
-
|
Uncertainty-Aware Action Repeating Options ( Poster ) > link | Joongkyu Lee 路 Seung Joon Park 路 Yunhao Tang 路 Min-hwan Oh 馃敆 |
-
|
Robust Driving Across Scenarios via Multi-residual Task Learning ( Poster ) > link | Vindula Jayawardana 路 Sirui Li 路 Cathy Wu 路 Yashar Farid 路 Kentaro Oguchi 馃敆 |
-
|
Forecaster: Towards Temporally Abstract Tree-Search Planning from Pixels ( Poster ) > link | Thomas Jiralerspong 路 Flemming Kondrup 路 Doina Precup 路 Khimya Khetarpal 馃敆 |
-
|
A Study of Generalization in Offline Reinforcement Learning ( Poster ) > link | Ishita Mediratta 路 Qingfei You 路 Minqi Jiang 路 Roberta Raileanu 馃敆 |