https://github.com/openai/baselines
Tip revision: f05b716b03edb810fb61b2bca0006591c736bdd6 authored by Peter Zhokhov on 14 November 2018, 19:01:05 UTC
trpo - increase reward and eplen buffer to 100 for consistency
trpo - increase reward and eplen buffer to 100 for consistency
Tip revision: f05b716
| File | Mode | Size |
|---|---|---|
| baselines | ||
| data | ||
| docs | ||
| .benchmark_pattern | -rw-r--r-- | 1 byte |
| .gitignore | -rw-r--r-- | 283 bytes |
| .travis.yml | -rw-r--r-- | 239 bytes |
| Dockerfile | -rw-r--r-- | 459 bytes |
| LICENSE | -rw-r--r-- | 1.1 KB |
| README.md | -rw-r--r-- | 7.3 KB |
| benchmarks_atari10M.htm | -rw-r--r-- | 425.1 KB |
| benchmarks_mujoco1M.htm | -rw-r--r-- | 153.0 KB |
| setup.cfg | -rw-r--r-- | 133 bytes |
| setup.py | -rw-r--r-- | 1.6 KB |
