⚡ Classification diagram
https://miro.com/app/board/uXjVO67mfJM=/?share_link_id=10266379307
📄 Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
Karl Pertsch,*Oleh Rybkin,*Frederik Ebert,Chelsea Finn,Dinesh Jayaraman,Sergey Levine
[Paper] [Video] [Github] NeurIPS 2020
📄 Semi-Parametric Topological Memory for Navigation
Nikolay Savinov, Alexey Dosovitskiy, Vladlen Koltun
(ICLR) 2018 [Paper] [Video] [Github]
📄 Efficient Planning in a Compact Latent Action Space
Zhengyao Jiang, Tianjun Zhang, Michael Janner, Yueying Li, Tim Rocktäschel, Edward Grefenstette, Yuandong Tian
[Paper][Github]
📄 Transformers are Sample Efficient World Models
Vincent Micheli, Eloi Alonso, François Fleuret
[Paper][Github]
📄 Decision Transformer: Reinforcement Learning via Sequence Modeling
ili Chen*, Kevin Lu*, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas*, Igor Mordatch*
ICML 2021[Paper][Github]
📄 Deep Hierarchical Planning from Pixels
Danijar Hafner, Kuang-Huei Lee, Ian Fischer, Pieter Abbeel
[Paper] [Website]
📄 A Generalist Agent
Scott Reed, Konrad Zolna, ..., Mahyar Bordbar, Nando de Freitas
[Paper] [Website]
📄 Average-Reward Learning and Planning with Options
Yi Wan, Abhishek Naik, Richard S. Sutton
[Paper]
📄 Dynamics-Aware Unsupervised Discovery of Skills
Archit Sharma, Shixiang Gu, Sergey Levine, Vikash Kumar, Karol Hausman
[Paper]
📄 Sparse Graphical Memory for Robust Planning
Scott Emmons, Ajay Jain, ..., Pieter Abbeel, Deepak Pathak
[Paper]
📄 Planning with Goal-Conditioned Policies
Soroush Nasiriany, Vitchyr Pong, Steven Lin, Sergey Levine
[Paper] [Website] [GitHub]
📄 Learning Space Partitions for Path Planning
Kevin Yang, Tianjun Zhang, ..., Dan Klein, Yuandong Tian
[Paper]
📄 Cognitive Mapping and Planning for Visual Navigation
Saurabh Gupta, Varun Tolani, ..., Rahul Sukthankar, Jitendra Malik
[Paper] [GitHub]
📄 Toward Discovering Options that Achieve Faster Planning
Yi Wan, Richard S. Sutton
[Paper]
📄 Vector Quantized Models for Planning
Sherjil Ozair, Yazhe Li, ..., Aäron van den Oord, Oriol Vinyals
[Paper]
📄 History Aware Multimodal Transformer for Vision-and-Language Navigation
Shizhe Chen, Pierre-Louis Guhur, Cordelia Schmid, Ivan Laptev
[Paper]
📄 Hallucinative Topological Memory for Zero-Shot Visual Planning
https://arxiv.org/abs/2002.12336
📄 World Model as a Graph: Learning Latent Landmarks for Planning
https://proceedings.mlr.press/v139/zhang21x.html
📄 Discovering and Achieving Goals via World Models
https://danijar.com/project/lexa
📄 Planning to Explore via Self-Supervised World Models
https://ramanans1.github.io/plan2explore
📄 Search on the Replay Buffer: Bridging Planning and Reinforcement Learning
https://arxiv.org/abs/1906.05253
📄 Floyd-Warshall Reinforcement Learning: Learning from Past Experiences to Reach New Goals
https://arxiv.org/abs/1809.09318
📄 Generalized Hindsight for Reinforcement Learning
https://arxiv.org/abs/2002.11708.
📄 Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay
https://arxiv.org/pdf/2108.07887.pdf
📄 Rapid Exploration for Open-World Navigation with Latent Goal Models
https://arxiv.org/abs/2104.05859
https://openreview.net/pdf?id=d_SWJhyKfVw
📄 InfoBot: Transfer and Exploration via the Information Bottleneck
https://arxiv.org/abs/1901.10902
📄 Learning an embedding space for transferable robot skills
https://openreview.net/forum?id=rk07ZXZRb
📄 Parrot: Data-Driven Behavioral Priors for Reinforcement Learning
https://arxiv.org/abs/2011.10024
📄 ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation
http://svl.stanford.edu/projects/relmogen
📄 HalGan:Addressing Sample Complexity in Visual Tasks Using HER and Hallucinatory GANs
https://arxiv.org/pdf/1901.11529.pdf
📄 Long Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
https://orybkin.github.io/video-gcp/
📄 Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks
https://arxiv.org/abs/2107.06405
📄 Learning One Representation to Optimize All Rewards
https://arxiv.org/abs/2103.07945
📄 Model-Based Reinforcement Learning via Latent-Space Collocation
https://orybkin.github.io/latco/
📄 Automatic Goal Generation for Reinforcement Learning Agents
https://arxiv.org/abs/1705.06366
📄 Skill Preferences: Learning to Extract and Execute Skills from Human Feedback
https://sites.google.com/view/skill-pref.
📄 Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement learning
https://arxiv.org/abs/2111.03189
📄 Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning
https://arxiv.org/abs/2006.11485
📄 Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning
https://t.co/yJqJwwCT6r
📄 A First-Occupancy Representation for Reinforcement Learning
https://arxiv.org/abs/2109.13863
📄Skill Discovery for Exploration and Planning using Deep Skill Graphs
https://sites.google.com/brown.edu/dsg/
📄Deep Skill Chaining
http://sites.google.com/g.hmc.edu/dsc/
📄Flexible Option Learning
https://openreview.net/pdf?id=L5vbEVIePyb.
📄Finding Options that minimize planning time
http://proceedings.mlr.press/v97/jinnai19a/jinnai19a.pdf
📄Discovering Options for Exploration by Minimizing Cover Time
http://proceedings.mlr.press/v97/jinnai19b/jinnai19b.pdf
📄Successor Options
https://arxiv.org/pdf/1905.05731.pdf
📄causal InfoGan
https://sites.google.com/view/causal-infogan/home
📄 Planning with Diffusion for Flexible Behavior Synthesis
https://diffusion-planning.github.io/
📄 Learning Robot Skills with Temporal Variational Inference https://arxiv.org/abs/2006.16232
📄 Learning Geometric Reasoning and Control for Long-Horizon Tasks from Visual Input
https://ieeexplore.ieee.org/abstract/document/9560934
http://groups.csail.mit.edu/robotics-center/public_papers/Driess21.pdf
📺 https://youtu.be/AcPWRTkr3_g
📄 Learning to solve sequential physical reasoning problems from a scene image
https://journals.sagepub.com/doi/full/10.1177/02783649211056967
📄 Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Image
https://arxiv.org/abs/2006.05398
📄 Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs
https://arxiv.org/abs/2012.07277
📺 https://www.youtube.com/watch?v=GCfs3DJ4aO4
📄 Differentiable Physics and Stable Modes for Tool-Use and Manipulation Planning
http://www.roboticsproceedings.org/rss14/p44.pdf
📺 https://youtu.be/ILufu3Iq2SI
📄 Goal-Conditioned Reinforcement Learning with Imagined Subgoals
https://proceedings.mlr.press/v139/chane-sane21a.html
📺 https://crossminds.ai/video/goal-conditioned-reinforcement-learning-with-imagined-subgoals-614bcccc3c7a224a90902b87/
https://github.com/elliotchanesane31/RIS
📄 Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning
https://ieeexplore.ieee.org/abstract/document/8593871?casa_token=IBsv3HtFInsAAAAA:IgK0ydhMyvhyJjUmZw5dqv1Sx4cJhjZEOdAGBwqdhnJJaM05MvJ7lL4WaC6aOREFE64N3G4sVzPpNg
https://github.com/mit-acl/cadrl_ros
📄 Learning Sampling Distributions for Robot Motion Planning
https://ieeexplore.ieee.org/abstract/document/8460730
arxiv-https://arxiv.org/abs/1709.05448
https://github.com/StanfordASL/LearnedSamplingDistributions
📄 Motion Planning Networks
https://ieeexplore.ieee.org/abstract/document/8793889
arxiv- https://arxiv.org/abs/1806.05767
📺https://www.youtube.com/watch?v=hT8hsptcwLw
📄 Robot Motion Planning in Learned Latent Spaces
https://ieeexplore.ieee.org/abstract/document/8653875
https://github.com/StanfordASL/LSBMP
📄 Neural Path Planning:Fixed Time,Near-Optimal Path Generation via Oracle Imitation
https://arxiv.org/abs/1904.11102