FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037655992> ?p ?o ?g. }

• W3037655992 abstract "We propose a simple, practical, and intuitive approach for domain adaptation in reinforcement learning. Our approach stems from the idea that the agent's experience in the source domain should look similar to its experience in the target domain. Building off of a probabilistic view of RL, we formally show that we can achieve this goal by compensating for the difference in dynamics by modifying the reward function. This modified reward function is simple to estimate by learning auxiliary classifiers that distinguish source-domain transitions from target-domain transitions. Intuitively, the modified reward function penalizes the agent for visiting states and taking actions in the source domain which are not possible in the target domain. Said another way, the agent is penalized for transitions that would indicate that the agent is interacting with the source domain, rather than the target domain. Our approach is applicable to domains with continuous states and actions and does not require learning an explicit model of the dynamics. On discrete and continuous control tasks, we illustrate the mechanics of our approach and demonstrate its scalability to high-dimensional tasks." @default.
• W3037655992 created "2020-07-02" @default.
• W3037655992 creator A5026322200 @default.
• W3037655992 creator A5035051008 @default.
• W3037655992 creator A5069381618 @default.
• W3037655992 creator A5071983998 @default.
• W3037655992 creator A5091446143 @default.
• W3037655992 date "2020-06-24" @default.
• W3037655992 modified "2023-09-27" @default.
• W3037655992 title "Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers" @default.
• W3037655992 cites W122050270 @default.
• W3037655992 cites W1500462030 @default.
• W3037655992 cites W1510402218 @default.
• W3037655992 cites W1511986666 @default.
• W3037655992 cites W1522301498 @default.
• W3037655992 cites W1548614216 @default.
• W3037655992 cites W1564393562 @default.
• W3037655992 cites W1585575029 @default.
• W3037655992 cites W1679855469 @default.
• W3037655992 cites W1731081199 @default.
• W3037655992 cites W1809653203 @default.
• W3037655992 cites W189742998 @default.
• W3037655992 cites W1907796993 @default.
• W3037655992 cites W1966026565 @default.
• W3037655992 cites W1978161072 @default.
• W3037655992 cites W1978380814 @default.
• W3037655992 cites W1980035368 @default.
• W3037655992 cites W2014512216 @default.
• W3037655992 cites W2026659355 @default.
• W3037655992 cites W2032536435 @default.
• W3037655992 cites W2042357378 @default.
• W3037655992 cites W2042520683 @default.
• W3037655992 cites W2080039641 @default.
• W3037655992 cites W2097381042 @default.
• W3037655992 cites W2098284983 @default.
• W3037655992 cites W2102689555 @default.
• W3037655992 cites W2103851188 @default.
• W3037655992 cites W2104068492 @default.
• W3037655992 cites W2105143952 @default.
• W3037655992 cites W2107464055 @default.
• W3037655992 cites W2121703796 @default.
• W3037655992 cites W2122136962 @default.
• W3037655992 cites W2123459560 @default.
• W3037655992 cites W2140135625 @default.
• W3037655992 cites W2145060720 @default.
• W3037655992 cites W2158796564 @default.
• W3037655992 cites W2165792602 @default.
• W3037655992 cites W2171370495 @default.
• W3037655992 cites W2197493596 @default.
• W3037655992 cites W2255883267 @default.
• W3037655992 cites W2268119109 @default.
• W3037655992 cites W2408670836 @default.
• W3037655992 cites W24477102 @default.
• W3037655992 cites W2528489519 @default.
• W3037655992 cites W2529477964 @default.
• W3037655992 cites W2529989861 @default.
• W3037655992 cites W2530741948 @default.
• W3037655992 cites W2562192638 @default.
• W3037655992 cites W2562736583 @default.
• W3037655992 cites W2565902248 @default.
• W3037655992 cites W2578206533 @default.
• W3037655992 cites W2580909119 @default.
• W3037655992 cites W2586431331 @default.
• W3037655992 cites W2590953969 @default.
• W3037655992 cites W2591984255 @default.
• W3037655992 cites W2593800221 @default.
• W3037655992 cites W2594374979 @default.
• W3037655992 cites W2605102758 @default.
• W3037655992 cites W2618318883 @default.
• W3037655992 cites W2736601468 @default.
• W3037655992 cites W2738129230 @default.
• W3037655992 cites W2739083961 @default.
• W3037655992 cites W2769541360 @default.
• W3037655992 cites W2781726626 @default.
• W3037655992 cites W2785542264 @default.
• W3037655992 cites W2785738552 @default.
• W3037655992 cites W2794757725 @default.
• W3037655992 cites W2799151646 @default.
• W3037655992 cites W2801572960 @default.
• W3037655992 cites W2807484975 @default.
• W3037655992 cites W2808217720 @default.
• W3037655992 cites W2808849637 @default.
• W3037655992 cites W2904453761 @default.
• W3037655992 cites W2949608212 @default.
• W3037655992 cites W2950004691 @default.
• W3037655992 cites W2950560720 @default.
• W3037655992 cites W2951881474 @default.
• W3037655992 cites W2952042413 @default.
• W3037655992 cites W2962736495 @default.
• W3037655992 cites W2962793481 @default.
• W3037655992 cites W2962803570 @default.
• W3037655992 cites W2962899390 @default.
• W3037655992 cites W2963277051 @default.
• W3037655992 cites W2963394426 @default.
• W3037655992 cites W2963412383 @default.
• W3037655992 cites W2963508354 @default.
• W3037655992 cites W2963674921 @default.
• W3037655992 cites W2963960193 @default.
• W3037655992 cites W2964349150 @default.
• W3037655992 cites W2968116426 @default.

• next