Adaptive Agents in Minecraft: A Hybrid Paradigm for Combining Domain Knowledge with Reinforcement Learning

@inproceedings{Parashar2017AdaptiveAI,
  title={Adaptive Agents in Minecraft: A Hybrid Paradigm for Combining Domain Knowledge with Reinforcement Learning},
  author={Priyam Parashar and Bradley Sheneman and Ashok K. Goel},
  booktitle={AAMAS Workshops},
  year={2017}
}
We present a pilot study focused on creating flexible Hierarchical Task Networks that can leverage Reinforcement Learning to repair and adapt incomplete plans in the simulated rich domain of Minecraft. [...] Key Result Results from simulations indicate that a combined approach using both HTN and RL is more flexible than HTN alone and more efficient than RL alone.Expand
Conceptualization and Implementation of a Reinforcement Learning Approach Using a Case-Based Reasoning Agent in a FPS Scenario
TLDR
This paper proposes a FPS agent who is using a combination of case-based reasoning and reinforcement learning to improve the overall performance and describes the implementation of the reinforcement algorithm and the performed evaluation using different starting case bases.
Towards robust grasps: Using the environment semantics for robotic object affordances
TLDR
The business problem that motivated the innovation, Kiva technology and the benefits it brought to customers, and the future of applications of robotics in warehouses are explained, as well as examples of the kinds of things that mobile robots can learn over long autonomous operations in such environments.
Generating Instructions at Different Levels of Abstraction
TLDR
A crowdsourcing evaluation shows that the choice of abstraction level matters to users, and that an abstraction strategy which balances low-level and high-level object descriptions compares favorably to ones which don’t.

References

SHOWING 1-10 OF 32 REFERENCES
Integration of Online Learning into HTN Planning for Robotic Tasks
TLDR
The idea behind this work is to use the HTN domain to constrain the space of possibilities, and then to learn on the constrained space in a way requiring few training samples, rendering the method applicable to autonomous mobile robots.
Dynagent: An Incremental Forward-Chaining HTN Planning Agent in Dynamic Domains
TLDR
This paper presents the new agent algorithm that integrates forward-chaining HTN planning, execution, belief updates, and plan modifications, and shows that the algorithm is effective for the replanning problem of museum tour guide robots, which is similar to the replanie problem of a traveling salesman.
Combining Model-Based Meta-Reasoning and Reinforcement Learning for Adapting Game-Playing Agents
TLDR
The results indicate that in the task examined, model-based meta-reasoning coupled with reinforcement learning enables the agent to learn the task with performance matching that of an expert designed agent and with speed exceeding that of a pure reinforcement learning agent.
Learning to optimize mobile robot navigation based on HTN plans
TLDR
It is shown how a robot can learn to select plan transformations based on projections of its intended behavior, and the overall robot navigation performance is increased by almost 42 % when using learned projective models to selected plan transformations.
Learning hierarchical task networks by observation
TLDR
An approach that observes sequences of operators taken from expert solutions to problems and learns hierarchical task networks from them and has similarities to previous algorithms for explanation-based learning, but differs in its ability to acquire hierarchical structures and in the generality of learned conditions.
Using Model-Based Reflection to Guide Reinforcement Learning
In model-based reflection, an agent contains a model of its own reasoning processes organized via the tasks the agents must accomplish and the knowledge and methods required to accomplish these
Reinforcement learning in robotics: A survey
TLDR
This article attempts to strengthen the links between the two research communities by providing a survey of work in reinforcement learning for behavior generation in robots by highlighting both key challenges in robot reinforcement learning as well as notable successes.
Planner9, a HTN Planner Distributed on Groups of Miniature Mobile Robots
TLDR
This paper presents Planner9, a hierarchical task network (htn) planner that runs on groups of miniature mobile robots, which scales well with the number of robots, even on non-linear tasks that involve recursions in their decompositions.
Reinforcement Learning: An Introduction
TLDR
This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.
A survey of robot learning from demonstration
TLDR
A comprehensive survey of robot Learning from Demonstration (LfD), a technique that develops policies from example state to action mappings, which analyzes and categorizes the multiple ways in which examples are gathered, as well as the various techniques for policy derivation.
...
1
2
3
4
...