add RECUR

README.md

@@ -84,7 +84,7 @@ Explicitly show the relationships between various techniques of deep reinforceme
 * [Multiagent Bidirectionally-Coordinated Nets for Learning to Play StarCraft Combat Games](BiCNet.md) 29 Mar 2017
 
 ## New design
-
+* [Reverse Curriculum Generation for Reinforcement Learning](RECUR.md)
 * [Learning to Design Games: Strategic Environments in Deep Reinforcement Learning](DualMDP.md) 5 July 2017
 
 ## Multitask

RECUR.md

@@ -0,0 +1,5 @@
+# Reverse Curriculum Generation for Reinforcement Learning
+
+Carlos Florensa, David Held, Markus Wulfmeier, Pieter Abbeel
+
+Many relevant tasks require an agent to reach a certain state, or to manipulate objects into a desired configuration. For example, we might want a robot to align and assemble a gear onto an axle or insert and turn a key in a lock. These tasks present considerable difficulties for reinforcement learning approaches, since the natural reward function for such goal-oriented tasks is sparse and prohibitive amounts of exploration are required to reach the goal and receive a learning signal. Past approaches tackle these problems by manually designing a task-specific reward shaping function to help guide the learning. Instead, we propose a method to learn these tasks without requiring any prior task knowledge other than obtaining a single state in which the task is achieved. The robot is trained in "reverse", gradually learning to reach the goal from a set of starting positions increasingly far from the goal. Our method automatically generates a curriculum of starting positions that adapts to the agent's performance, leading to efficient training on such tasks. We demonstrate our approach on difficult simulated fine-grained manipulation problems, not solvable by state-of-the-art reinforcement learning methods.