Matches in SemOpenAlex for { <https://semopenalex.org/work/W1496204003> ?p ?o ?g. }
- W1496204003 abstract "Coaching is a relationship where one agent provides advice to another about how to act. This thesis explores a range of problems faced by an automated coach agent in providing advice to one or more automated advice-receiving agents. The coach's job is to help the agents perform as well as possible in their environment. We identify and address a set of technical challenges: How can the coach learn and use models of the environment? How should advice be adapted to the peculiarities of the advice receivers? How can opponents be modeled, and how can those models be used? How should advice be represented to be effectively used by a team? This thesis serves both to define the coaching problem and explore solutions to the challenges posed. This thesis is inspired by a simulated robot soccer environment with a coach agent who can provide advice to a team in a standard language. This author developed, in collaboration with others, this coach environment and standard language as the thesis progressed. The experiments in this thesis represent the largest known empirical study in the simulated robot soccer environment. A predator-prey domain and a moving maze environment are used for additional experimentation. All algorithms are implemented in at least one of these environments and empirical validation is performed. In addition to the coach problem formulation and decompositions, the thesis makes several main technical contributions: (i) Several opponent model representations with associated learning algorithms, whose effectiveness in the robot soccer domain is demonstrated. (ii) A study of the effects and need for coach learning under various limitations of the advice receiver and communication bandwidth. (iii) The Multi-Agent Simple Temporal Network, a multi-agent plan representation which is refinement of a Simple Temporal Network, with an associated distributed plan execution algorithm. (iv) Algorithms for learning an abstract Markov Decision Process from external observations, a given state abstraction, and partial abstract action templates. The use of the learned MDP for advice is explored in various scenarios." @default.
- W1496204003 created "2016-06-24" @default.
- W1496204003 creator A5075031230 @default.
- W1496204003 creator A5088276691 @default.
- W1496204003 date "2005-01-01" @default.
- W1496204003 modified "2023-09-25" @default.
- W1496204003 title "Coaching: learning and using environment and agent models for advice" @default.
- W1496204003 cites W101508493 @default.
- W1496204003 cites W1480866642 @default.
- W1496204003 cites W1484740474 @default.
- W1496204003 cites W1489410353 @default.
- W1496204003 cites W1497976081 @default.
- W1496204003 cites W1502996661 @default.
- W1496204003 cites W1505354086 @default.
- W1496204003 cites W1511887321 @default.
- W1496204003 cites W1515086648 @default.
- W1496204003 cites W1521003796 @default.
- W1496204003 cites W1521835442 @default.
- W1496204003 cites W1528674883 @default.
- W1496204003 cites W1533701715 @default.
- W1496204003 cites W1536258751 @default.
- W1496204003 cites W1536295095 @default.
- W1496204003 cites W1538418248 @default.
- W1496204003 cites W1540685400 @default.
- W1496204003 cites W1544444076 @default.
- W1496204003 cites W1552645109 @default.
- W1496204003 cites W1559754312 @default.
- W1496204003 cites W1560608393 @default.
- W1496204003 cites W1562091114 @default.
- W1496204003 cites W1564534945 @default.
- W1496204003 cites W1575638943 @default.
- W1496204003 cites W1575890684 @default.
- W1496204003 cites W1588316674 @default.
- W1496204003 cites W1589901344 @default.
- W1496204003 cites W1590759229 @default.
- W1496204003 cites W1593296915 @default.
- W1496204003 cites W1594602740 @default.
- W1496204003 cites W1598975024 @default.
- W1496204003 cites W1657704689 @default.
- W1496204003 cites W1757815404 @default.
- W1496204003 cites W1777239053 @default.
- W1496204003 cites W1783774027 @default.
- W1496204003 cites W1808725644 @default.
- W1496204003 cites W1817981642 @default.
- W1496204003 cites W1824415582 @default.
- W1496204003 cites W1849223937 @default.
- W1496204003 cites W1908422888 @default.
- W1496204003 cites W1966028617 @default.
- W1496204003 cites W1975165872 @default.
- W1496204003 cites W1976115983 @default.
- W1496204003 cites W1986535023 @default.
- W1496204003 cites W1990616668 @default.
- W1496204003 cites W1992880122 @default.
- W1496204003 cites W1996389440 @default.
- W1496204003 cites W1998754086 @default.
- W1496204003 cites W1999808895 @default.
- W1496204003 cites W2006719510 @default.
- W1496204003 cites W2012508367 @default.
- W1496204003 cites W2015040676 @default.
- W1496204003 cites W2016288462 @default.
- W1496204003 cites W201917955 @default.
- W1496204003 cites W2020294948 @default.
- W1496204003 cites W2020764470 @default.
- W1496204003 cites W2033697467 @default.
- W1496204003 cites W2035078485 @default.
- W1496204003 cites W2043997854 @default.
- W1496204003 cites W2067840831 @default.
- W1496204003 cites W2067905901 @default.
- W1496204003 cites W2070301851 @default.
- W1496204003 cites W2076064414 @default.
- W1496204003 cites W2077400689 @default.
- W1496204003 cites W2077902449 @default.
- W1496204003 cites W2081219538 @default.
- W1496204003 cites W2093103468 @default.
- W1496204003 cites W2094849970 @default.
- W1496204003 cites W2097744910 @default.
- W1496204003 cites W2099111195 @default.
- W1496204003 cites W2099144379 @default.
- W1496204003 cites W2099347601 @default.
- W1496204003 cites W2100058274 @default.
- W1496204003 cites W2101782549 @default.
- W1496204003 cites W2103034445 @default.
- W1496204003 cites W2106887613 @default.
- W1496204003 cites W2107280071 @default.
- W1496204003 cites W2107766840 @default.
- W1496204003 cites W2109910161 @default.
- W1496204003 cites W2110415190 @default.
- W1496204003 cites W2110630796 @default.
- W1496204003 cites W2111063504 @default.
- W1496204003 cites W2117949203 @default.
- W1496204003 cites W2119120935 @default.
- W1496204003 cites W2120591602 @default.
- W1496204003 cites W2121517924 @default.
- W1496204003 cites W2124129360 @default.
- W1496204003 cites W2125055259 @default.
- W1496204003 cites W2128353691 @default.
- W1496204003 cites W2130182605 @default.
- W1496204003 cites W2133632477 @default.
- W1496204003 cites W2134779831 @default.
- W1496204003 cites W2137647991 @default.