Travelled to:1 × Australia
1 × Italy
1 × USA
Collaborated with:M.R.K.Ryan T.J.Perkins M.McGarity
Talks about:learn (4) reinforc (3) domain (2) architectur (1) experiment (1) markovian (1) theoret (1) partial (1) modular (1) analysi (1)
Person: Mark D. Pendrith
DBLP: Pendrith:Mark_D=
Contributed to:
200219981996Wrote 4 papers:
- ICML-2002-PerkinsP #fixpoint #on the
- On the Existence of Fixed Points for Q-Learning and Sarsa in Partially Observable Domains (TJP, MDP), pp. 490–497.
- ICML-1998-PendrithM #analysis #learning #markov
- An Analysis of Direct Reinforcement Learning in Non-Markovian Domains (MDP, MM), pp. 421–429.
- ICML-1998-RyanP #architecture #composition #learning #named
- RL-TOPS: An Architecture for Modularity and Re-Use in Reinforcement Learning (MRKR, MDP), pp. 481–487.
- ICML-1996-PendrithR #difference #learning
- Actual Return Reinforcement Learning versus Temporal Differences: Some Theoretical and Experimental Results (MDP, MRKR), pp. 373–381.