Commits · master · Samuele Tosatto / Optimistic-DQN

13 Aug, 2018 2 commits
- update and bug fix · bc12d7a2
  tosatto authored Aug 13, 2018
  
  bc12d7a2
- update and bug fix · 5515abfe
  tosatto authored Aug 13, 2018
  
  5515abfe
10 Aug, 2018 1 commit
- fix by carlo · fbb58490
  tosatto authored Aug 10, 2018
  
  fbb58490
03 Aug, 2018 4 commits
- buf fixing. memory should not increase anymore · d823afdd
  tosatto authored Aug 03, 2018
  
  d823afdd
- fixed in the right way the shape · 1d8b808d
  tosatto authored Aug 03, 2018
  
  1d8b808d
- memory usage · 9c2cf742
  tosatto authored Aug 03, 2018
  
  9c2cf742
- no parallelism for DQN atari · 3a1c4a1a
  tosatto authored Aug 03, 2018
  
  3a1c4a1a
02 Aug, 2018 7 commits
- partial dirty solution · 38bb1289
  tosatto authored Aug 02, 2018
  
  38bb1289
- Big bug corrected · 024ad8e7
  tosatto authored Aug 02, 2018
  
  024ad8e7
- bug fixing 1 · 3247ed30
  tosatto authored Aug 02, 2018
  
  3247ed30
- bug fixing · 89fce7d2
  tosatto authored Aug 02, 2018
  
  89fce7d2
- fix in replacement · dac62a91
  Carlo authored Aug 02, 2018
  
  dac62a91
- replacement flag added · 2a077115
  Carlo authored Aug 02, 2018
  
  2a077115
- memory optimization · 60afbb3d
  tosatto authored Aug 02, 2018
  
  60afbb3d
01 Aug, 2018 3 commits
- save settings within the experiment folder · 9b0d8bed
  tosatto authored Aug 01, 2018
  
  9b0d8bed
- memorizing time for learning · 7c3849ce
  tosatto authored Aug 01, 2018
  
  7c3849ce
- statistic for checking time of replay memory · 4948f6b2
  tosatto authored Aug 01, 2018
  
  4948f6b2
31 Jul, 2018 3 commits
- Lazy frames · e1e50bc7
  tosatto authored Jul 31, 2018
  
  e1e50bc7
- normalization of gradient is now a parameter · 6ef4d29b
  tosatto authored Jul 31, 2018
  
  6ef4d29b
- sqrt after · dee3e27d
  tosatto authored Jul 31, 2018
  
  dee3e27d
30 Jul, 2018 3 commits
- bug fixing · a63baa5f
  tosatto authored Jul 30, 2018
  
  a63baa5f
- Fix · 462a1d19
  tosatto authored Jul 30, 2018
  
  462a1d19
- MRSPropModified and default setting with initial exploration · 6ff4e38a
  tosatto authored Jul 30, 2018
  
  6ff4e38a
27 Jul, 2018 1 commit
- different statistics · d3c3cff3
  tosatto authored Jul 27, 2018
  
  d3c3cff3
26 Jul, 2018 6 commits
- Merge branch 'master' of git.ias.informatik.tu-darmstadt.de:tosatto/Optimistic-DQN · 1221ffc9
  tosatto authored Jul 26, 2018
  
  1221ffc9
- save also statistics · f5d31f44
  tosatto authored Jul 26, 2018
  
  f5d31f44
- default parameters updated · 7ace5eea
  Carlo authored Jul 26, 2018
  
  7ace5eea
- 2500 target_update_frequency · 85d1d865
  Carlo authored Jul 26, 2018
  
  85d1d865
- n_core · b1d32c71
  tosatto authored Jul 26, 2018
  
  b1d32c71
- Exploration/Exploitation + experiments · 204642dc
  tosatto authored Jul 26, 2018
  
  204642dc
25 Jul, 2018 1 commit
- run statistics for taxi environment · 4645f715
  tosatto authored Jul 25, 2018
  
  4645f715
24 Jul, 2018 3 commits
- Atari with statistics · 28306e35
  tosatto authored Jul 24, 2018
  
  28306e35
- minor changes · 4bce32ce
  tosatto authored Jul 24, 2018
  
  4bce32ce
- Improvement in ODQN · fd2262cb
  tosatto authored Jul 24, 2018
  
  fd2262cb
22 Jul, 2018 1 commit
- Bug in the formula corrected · 0eec94cb
  tosatto authored Jul 22, 2018
  
  0eec94cb
21 Jul, 2018 2 commits
- bug fixing · 15346156
  tosatto authored Jul 21, 2018
  
  15346156
- Formula corrected for propagated bonus · 9888c5a3
  tosatto authored Jul 21, 2018
  
  9888c5a3
20 Jul, 2018 2 commits
- bug fixing · 92c72313
  tosatto authored Jul 20, 2018
  
  92c72313
- bug fixing · 2c9a2a07
  tosatto authored Jul 20, 2018
  
  2c9a2a07
19 Jul, 2018 1 commit
- Merge branch 'master' of git.ias.informatik.tu-darmstadt.de:tosatto/Optimistic-DQN · 6228d2a4
  tosatto authored Jul 19, 2018
  
  6228d2a4