Main » Publications by Topic
This list is automatically created, please see publications by year in order to have a more chronological overview on my publications. Note that the list on this page is automatically generated and as such always overlapping due to overlapping keywords.
Reinforcement Learning
| Record Number | 1773 |
| Reference Type | Report |
| Author(s) | Kwee, I.;Hutter, M.;Schmidhuber, J. |
| Year | 2001 |
| Title | Gradient-based reinforcement planning in policy-search methods |
| Keywords | reinforcement learning policy gradients model-based |
| Notes | An interesting paper that derives the policy gradient theorem in a differernt way for discrete worlds. Jan work is a clear superset of this. The authors achieve efficient learning by learning the model (state transition probs). All can be formluated nicely in Jan's RL framework |
| Place Published | Manno CH-6928, Switzerland |
| Publisher | IDSIA |
| Short Title | Gradient-based reinforcement planning in policy-search methods |
| ISBN/ISSN | IDSIA-14-01 |
| URL(s) | http://www-clmc.usc.edu/publications/K/kwee-TR-IDSIA-14-01.pdf |
Control
| Record Number | 1773 |
| Reference Type | Report |
| Author(s) | Kwee, I.;Hutter, M.;Schmidhuber, J. |
| Year | 2001 |
| Title | Gradient-based reinforcement planning in policy-search methods |
| Keywords | reinforcement learning policy gradients model-based |
| Notes | An interesting paper that derives the policy gradient theorem in a differernt way for discrete worlds. Jan work is a clear superset of this. The authors achieve efficient learning by learning the model (state transition probs). All can be formluated nicely in Jan's RL framework |
| Place Published | Manno CH-6928, Switzerland |
| Publisher | IDSIA |
| Short Title | Gradient-based reinforcement planning in policy-search methods |
| ISBN/ISSN | IDSIA-14-01 |
| URL(s) | http://www-clmc.usc.edu/publications/K/kwee-TR-IDSIA-14-01.pdf |
Learning Motor Primitives
| Record Number | 1773 |
| Reference Type | Report |
| Author(s) | Kwee, I.;Hutter, M.;Schmidhuber, J. |
| Year | 2001 |
| Title | Gradient-based reinforcement planning in policy-search methods |
| Keywords | reinforcement learning policy gradients model-based |
| Notes | An interesting paper that derives the policy gradient theorem in a differernt way for discrete worlds. Jan work is a clear superset of this. The authors achieve efficient learning by learning the model (state transition probs). All can be formluated nicely in Jan's RL framework |
| Place Published | Manno CH-6928, Switzerland |
| Publisher | IDSIA |
| Short Title | Gradient-based reinforcement planning in policy-search methods |
| ISBN/ISSN | IDSIA-14-01 |
| URL(s) | http://www-clmc.usc.edu/publications/K/kwee-TR-IDSIA-14-01.pdf |
Robotics
| Record Number | 1773 |
| Reference Type | Report |
| Author(s) | Kwee, I.;Hutter, M.;Schmidhuber, J. |
| Year | 2001 |
| Title | Gradient-based reinforcement planning in policy-search methods |
| Keywords | reinforcement learning policy gradients model-based |
| Notes | An interesting paper that derives the policy gradient theorem in a differernt way for discrete worlds. Jan work is a clear superset of this. The authors achieve efficient learning by learning the model (state transition probs). All can be formluated nicely in Jan's RL framework |
| Place Published | Manno CH-6928, Switzerland |
| Publisher | IDSIA |
| Short Title | Gradient-based reinforcement planning in policy-search methods |
| ISBN/ISSN | IDSIA-14-01 |
| URL(s) | http://www-clmc.usc.edu/publications/K/kwee-TR-IDSIA-14-01.pdf |
Human Motor Control
| Record Number | 1773 |
| Reference Type | Report |
| Author(s) | Kwee, I.;Hutter, M.;Schmidhuber, J. |
| Year | 2001 |
| Title | Gradient-based reinforcement planning in policy-search methods |
| Keywords | reinforcement learning policy gradients model-based |
| Notes | An interesting paper that derives the policy gradient theorem in a differernt way for discrete worlds. Jan work is a clear superset of this. The authors achieve efficient learning by learning the model (state transition probs). All can be formluated nicely in Jan's RL framework |
| Place Published | Manno CH-6928, Switzerland |
| Publisher | IDSIA |
| Short Title | Gradient-based reinforcement planning in policy-search methods |
| ISBN/ISSN | IDSIA-14-01 |
| URL(s) | http://www-clmc.usc.edu/publications/K/kwee-TR-IDSIA-14-01.pdf |
Book Reviews
| Record Number | 1773 |
| Reference Type | Report |
| Author(s) | Kwee, I.;Hutter, M.;Schmidhuber, J. |
| Year | 2001 |
| Title | Gradient-based reinforcement planning in policy-search methods |
| Keywords | reinforcement learning policy gradients model-based |
| Notes | An interesting paper that derives the policy gradient theorem in a differernt way for discrete worlds. Jan work is a clear superset of this. The authors achieve efficient learning by learning the model (state transition probs). All can be formluated nicely in Jan's RL framework |
| Place Published | Manno CH-6928, Switzerland |
| Publisher | IDSIA |
| Short Title | Gradient-based reinforcement planning in policy-search methods |
| ISBN/ISSN | IDSIA-14-01 |
| URL(s) | http://www-clmc.usc.edu/publications/K/kwee-TR-IDSIA-14-01.pdf |
The majority of the publications can also be obtained by Google Scholar where incomplete lists of citations are also given.