Progress for week 16 (2018)

From Robin

(Difference between revisions)
Jump to: navigation, search
(Ny side: == Vetle Bu Solgård == === Budget === * === Accounting === * == Martin Hovin == === Budget === * === Accounting === *)
m (Vetle Bu Solgård)
 
(3 intermediate revisions not shown)
Line 1: Line 1:
== Vetle Bu Solgård ==
== Vetle Bu Solgård ==
=== Budget ===
=== Budget ===
-
*  
+
* Start DDPG and TRPO implementation
 +
* Make a decision and implement on where to validate algorithms
 +
* Extend REINFORCE with baseline
 +
* Read up on typical state representations and reward signals for locomotion tasks
 +
* Get an overview of potensial different tasks to explore with Dyret (Balance, movement speed, etc.)
=== Accounting ===
=== Accounting ===
-
*
+
* DDPG implemented and apparently working. TRPO implementation not started
 +
* Validating in continous mountaincar and Pendulum from openai gym environment
 +
* REINFORCE not working yet.
 +
* Not investigated. Trying to get the algorithm itself working first
 +
* Not thoroughly explored
== Martin Hovin ==
== Martin Hovin ==
=== Budget ===
=== Budget ===
-
*  
+
* Skrive resultater, diskusjon og konklusjon i Relearning
 +
* Skrive introduksjon
 +
* Skrive avsluttning på oppgaven
 +
 
=== Accounting ===
=== Accounting ===
-
*
+
* Skrevet første utkast til Relearning
 +
** For kort avsluttning?
 +
** Henger første halvdel sammen med siste?
 +
* Skrevet kort intro
 +
** Trengs det mer?
 +
** Må problemstillingen konkteriseres mer?
 +
* Startet på avsluttningen
 +
** Seksjonene er nå:
 +
:: Result summary
 +
:: Discussion summary
 +
:: Thesis conclusion
 +
:: Future work

Current revision as of 11:54, 20 April 2018

Contents

Vetle Bu Solgård

Budget

  • Start DDPG and TRPO implementation
  • Make a decision and implement on where to validate algorithms
  • Extend REINFORCE with baseline
  • Read up on typical state representations and reward signals for locomotion tasks
  • Get an overview of potensial different tasks to explore with Dyret (Balance, movement speed, etc.)

Accounting

  • DDPG implemented and apparently working. TRPO implementation not started
  • Validating in continous mountaincar and Pendulum from openai gym environment
  • REINFORCE not working yet.
  • Not investigated. Trying to get the algorithm itself working first
  • Not thoroughly explored

Martin Hovin

Budget

  • Skrive resultater, diskusjon og konklusjon i Relearning
  • Skrive introduksjon
  • Skrive avsluttning på oppgaven

Accounting

  • Skrevet første utkast til Relearning
    • For kort avsluttning?
    • Henger første halvdel sammen med siste?
  • Skrevet kort intro
    • Trengs det mer?
    • Må problemstillingen konkteriseres mer?
  • Startet på avsluttningen
    • Seksjonene er nå:
Result summary
Discussion summary
Thesis conclusion
Future work
Personal tools
Front page