nadavbh12 / Retro-Learning-Environment

The Retro Learning Environment (RLE) -- a learning framework for AI
Other
185 stars 40 forks source link

Test with DQN tensorflow version #12

Closed tohnperfect closed 7 years ago

tohnperfect commented 7 years ago

I try to modify the tensorflow DQN ALE version this repo to use RLE instead of ALE. However, I got the Segmentation fault error as follows,

I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcublas.so locally I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcudnn.so locally I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcufft.so locally I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcuda.so.1 locally I tensorflow/stream_executor/dso_loader.cc:128] successfully opened CUDA library libcurand.so locally Arguments: Namespace(compress_replay=False, core='./snes9x2010_libretro.so', eval_epoch_steps=125000, learning_rate=0.00025, model=None, normalize_weights=True, observation_steps=50000, prioritized_replay=False, replay_capacity=1000000, rom='./mortal_kombat.sfc', save_model_freq=10000, screen_capture_freq=250, target_model_update_freq=10000, train_epoch_steps=250000) Warning: couldn't load settings file: R.L.E: Retro Learning Environment (version 1.0.0) [Based upon the Arcade Learning Environment (A.L.E)] [Powered by LibRetro] Use -help for help screen. [inf] Frontend supports RGB565 - will use that instead of XRGB1555. Sound buffer size: 128000 (32000 samples) Core loaded [inf] No ROM file header found. Map_LoROMMap PPU.RenderSub = 0 PPU.FullClipping = 1 Settings.Transparency = 1 Settings.SpeedhackGameID = 0 PPU.SFXSpeedupHack = 0 coldata_update_screen = 1 [inf] "MORTAL KOMBAT" [checksum ok] LoROM, 16Mbits, ROM, NTSC, SRAM:0Kbits, ID:____, CRC32:DEF42945 Running ROM file... Random seed is 65 Segmentation fault (core dumped)

I did rename the rom file to agree with the name in the header file.

Please give me some advices?

nadavbh12 commented 7 years ago

hey @tohnperfect, Looks like there was a bug in the getRGB function. In addition to RGB, a fourth, currently unused, channel is returned for the alpha. It should work correctly now.