move to new location / add readme

yxy1995123 · Sep 5, 2018 · ea36cac · ea36cac
1 parent 9224a70
commit ea36cac
Show file tree

Hide file tree

Showing 5 changed files with 20 additions and 0 deletions.
diff --git a/README.md b/README.md
@@ -0,0 +1,20 @@
+# Reinforcement-Implementation
+
+This project aims to reproduce the results of several model-free RL algorithms in continuous action domain (mujuco environment).
+
+This projects
+* uses pytorch package
+* implements every algorithm independently in one file
+* is written in simplest style
+* tries to follow the original paper and reproduce their results
+
+My first stage of work is to reproduce this figure in the PPO paper.
+
+![](docs/ppo_experiments.png)
+
+- [x] A2C
+- [ ] ACER (A2C + Trust Region)
+- [ ] CEM
+- [x] TRPO (TRPO single path)
+- [x] PPO (PPO clip)
+- [ ] Vanilla PG, Adaptive
diff --git a/a2c.py → code/a2c.py b/a2c.py → code/a2c.py
diff --git a/ppo.py → code/ppo.py b/ppo.py → code/ppo.py
diff --git a/TRPO.py → code/trpo.py b/TRPO.py → code/trpo.py
diff --git a/docs/ppo_experiments.png b/docs/ppo_experiments.png