PRL Workshop Series

Bridging the Gap Between AI Planning and Reinforcement Learning

Bridging the Gap Between AI Planning and Reinforcement Learning (PRL) – Workshop at ICAPS 2021 (August 5-6)

< Link to other workshops in the series

This site presents the most up-to-date information about the workshop. Please, visit ICAPS 2021 for more general information.

While AI Planning and Reinforcement Learning communities focus on similar sequential decision-making problems, these communities remain somewhat unaware of each other on specific problems, techniques, methodologies, and evaluation.

This workshop aims to encourage discussion and collaboration between the researchers in the fields of AI planning and reinforcement learning. We aim to bridge the gap between the two communities, facilitate the discussion of differences and similarities in existing techniques, and encourage collaboration across the fields. We solicit interest from AI researchers that work in the intersection of planning and reinforcement learning, in particular, those that focus on intelligent decision making. As such, the joint workshop program is an excellent opportunity to gather a large and diverse group of interested researchers.


The workshop solicits work at the intersection of the fields of reinforcement learning and planning. We also solicit work solely in one area that can influence advances in the other so long as the connections are clearly articulated in the submission.

Submissions are invited for topics on, but not limited to:

Invited Speakers

Videos of all the invited talks.

Schedule – confirmed

The event will be fully virtual, consisting of:

The workshop program spans two days, August 5 and 6.

Thursday, August 5.

Videos of the contributed talks.

Time (EST)   Title
10:00 Invited Talk Danijar Hafner. General Infomax Agents through World Models
10:40 Contributed talk AI Planning Annotation in Reinforcement Learning: Options and Beyond
10:50 Contributed talk Efficient PAC Reinforcement Learning in Regular Decision Processes
11:00 Break  
11:15 Invited Talk Aviv Tamar. Learning to Plan and Planning to Learn
11:55 Discussion Session Abstractions in Planning & RL
12:15 Posters
13:15 Break  
13:30 Invited Talk Emma Brunskill. Careful Pessimism
14:10 Contributed talk Extending Graph Neural Networks for Generalized Stochastic Planning
14:20 Contributed talk First-Order Function Approximation for Transfer Learning in Relational MDPs
14:30 Contributed talk RePReL : Integrating Relational Planning and Reinforcement Learning for Effective Abstraction
14:40 Discussion Session Safe, Risk-sensitive, and Robust Planning and RL
15:00 End of day  

Friday, August 6.

Videos of the contributed talks.

Time (EST)   Title
10:00 Invited Talk André Barreto. The value equivalence principle for model-based reinforcement learning
10:40 Contributed talk Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators
10:50 Contributed talk Domain-independent reward machines for modular integration of planning and learning
11:00 Contributed talk Neural Network Heuristic Functions for Classical Planning : Reinforcement Learning and Comparison to Other Methods
11:10 Discussion Session Domain Generalization in Planning and RL
11:30 Break  
11:45 Invited Talk Elias Bareinboim. Towards Causal Reinforcement Learning
12:25 Contributed talk Neural Network Action Policy Verification via Predicate Abstraction
12:35 Contributed talk Debugging a Policy: A Framework for Automatic Action Policy Testing
12:45 Contributed talk AlwaysSafe: Reinforcement Learning without Safety Constraint Violations during Training
12:55 Discussion Session Next steps
13:25 Closing remarks  
13:30 (Optional) Break
13:45 (Optional) Additional Poster session
14:30 (Optional) End of day

Accepted submissions: papers and poster

Videos of the contributed talks

Accepted submissions

Submission Instructions

We solicit workshop paper submissions relevant to the above call of the following types:

Please format submissions in AAAI style (see instructions in the Author Kit 2021 at AAAI,

Some accepted long papers will be accepted as contributed talks. All accepted long and short papers and extended abstracts will be given a slot in the poster presentation session. Extended abstracts are intended as brief summaries of already published papers (a reference to the publication is expected), preliminary work, position papers or challenges that might help bridge the gap.

Paper submissions should be made through EasyChair,

Please send your inquiries by email to the organizers at

For up-to-date information, please visit the PRL website,

Important Dates

The reference timezone for all deadlines is UTC-12.

Previous Edition

PRL @ ICAPS 2020