Merge pull request #170 from zuoxingdong/step_info_trajectory

update VPG
zuoxingdong · May 8, 2019 · 351b45f · 351b45f
2 parents 79107a8 + 0175327
commit 351b45f
Show file tree

Hide file tree

Showing 160 changed files with 676 additions and 390 deletions.
diff --git a/baselines/README.md b/baselines/README.md
@@ -1,14 +1,20 @@
 This example includes the implementations of the following reinforcement learning algorithms:
 
-- [Cross Entropy Method (CEM)](cem)
-- [Covariance Matrix Adaptation Evolution Strategy (CMA-ES)](cmaes)
-- [OpenAI-ES](openaies)
-- [Vanilla Policy Gradient (VPG)](vpg)
-- [Proximal Policy Optimization (PPO)](ppo)
-- [Deep Deterministic Policy Gradients (DDPG)](ddpg)
-- [Twin Delayed DDPG (TD3)](td3)
-- [Soft Actor-Critic (SAC)](sac)
+- ES
+    - [Cross Entropy Method (CEM)](cem)
+    - [Covariance Matrix Adaptation Evolution Strategy (CMA-ES)](cmaes)
+    - [OpenAI-ES](openaies)
+- RL
+    - [Vanilla Policy Gradient (VPG)](vpg)
+    - [Proximal Policy Optimization (PPO)](ppo)
+    - [Deep Deterministic Policy Gradients (DDPG)](ddpg)
+    - [Twin Delayed DDPG (TD3)](td3)
+    - [Soft Actor-Critic (SAC)](sac)
 
 # Benchmarks
 
-<img src='benchmark.png' width='100%'>
+## ES
+<img src='benchmark_es.png' width='100%'>
+
+## RL
+<img src='benchmark_rl.png' width='100%'>
diff --git a/baselines/benchmark.png b/baselines/benchmark.png
diff --git a/baselines/benchmark_rl.png b/baselines/benchmark_rl.png