홈 › Papers

Beyond Tabula-Rasa: a Modular Reinforcement Learning Approach for Physically Embedded 3D Sokoban

2020-10-03 · Peter Karkus, Mehdi Mirza, Arthur Guez, Andrew Jaegle, Timothy Lillicrap, Lars Buesing, Nicolas Heess, Theophane Weber

Intelligent robots need to achieve abstract objectives using concrete, spatiotemporally complex sensory information and motor control. Tabula rasa deep reinforcement learning (RL) has tackled demanding tasks in terms of either visual, abstract, or physical reasoning, but solving these jointly remains a formidable challenge. One recent, unsolved benchmark task that integrates these challenges is Mujoban, where a robot needs to arrange 3D warehouses generated from 2D Sokoban puzzles. We explore whether integrated tasks like Mujoban can be solved by composing RL modules together in a sense-plan-act hierarchy, where modules have well-defined roles similarly to classic robot architectures. Unlike classic architectures that are typically model-based, we use only model-free modules trained with RL or supervised learning. We find that our modular RL approach dramatically outperforms the state-of-the-art monolithic RL agent on Mujoban. Further, learned modules can be reused when, e.g., using a different robot platform to solve the same task. Together our results give strong evidence for the importance of research into modular RL designs. Project website: https://sites.google.com/view/modular-rl/

📄 PDF Abstract BibTeX arXiv:2010.01298

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning (RL)Sokoban

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

2017-12-05 · David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou 외

The game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination of sophisticated search techniques, domain-specific adaptations, and handcr…

Game of Chess Game of Go Game of Shogi General Reinforcement Learning+3

Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress

2022-06-03 · Rishabh Agarwal, Max Schwarzer, Pablo Samuel Castro, Aaron Courville 외

Learning tabula rasa, that is without any prior knowledge, is the prevalent workflow in reinforcement learning (RL) research. However, RL systems, when applied to large-scale settings, rarely operate tabula rasa. Such la…

Atari Games Humanoid Control reinforcement-learning Reinforcement Learning+1

Heuristic-Guided Reinforcement Learning

2021-06-05 · NeurIPS 2021 12 · Ching-An Cheng, Andrey Kolobov, Adith Swaminathan

We provide a framework for accelerating reinforcement learning (RL) algorithms by heuristics constructed from domain knowledge or offline data. Tabula rasa RL algorithms require environment interactions or computation th…

Decision Making reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling

2023-01-28 · Kolby Nottingham, Prithviraj Ammanabrolu, Alane Suhr, Yejin Choi 외

Reinforcement learning (RL) agents typically learn tabula rasa, without prior knowledge of the world. However, if initialized with knowledge of high-level subgoals and transitions between subgoals, RL agents could utiliz…

Decision Making Minecraft Reinforcement Learning (RL)

Ranked Reward: Enabling Self-Play Reinforcement Learning for Combinatorial Optimization

2018-07-04 · Alexandre Laterre, Yunguan Fu, Mohamed Khalil Jabri, Alain-Sam Cohen 외

Adversarial self-play in two-player games has delivered impressive results when used with reinforcement learning algorithms that combine deep neural networks and tree search. Algorithms like AlphaZero and Expert Iteratio…

Combinatorial Optimization reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)