Addressing Function Approximation Error in Actor-Critic Methods

Code

• github.com/sfujim/TD3
  OfficialIn paperpytorch★ 0
• github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity
  pytorch★ 992
• github.com/intelligent-environments-lab/CityLearn
  tf★ 594
• github.com/arrival-ltd/catalyst-rl-tutorial
  pytorch★ 202
• github.com/fiorenza2/OffCon3
  pytorch★ 25
• github.com/core-robotics-lab/icct
  pytorch★ 18
• github.com/yydsok/oparl
  pytorch★ 18
• github.com/baturaysaglam/la3p
  pytorch★ 18
• github.com/seungju-k1m/sac-td3-td7
  pytorch★ 15
• github.com/GhadaSokar/Dynamic-Sparse-Training-for-Deep-Reinforcement-Learning
  pytorch★ 15

Abstract

In value-based reinforcement learning methods such as deep Q-learning, function approximation errors are known to lead to overestimated value estimates and suboptimal policies. We show that this problem persists in an actor-critic setting and propose novel mechanisms to minimize its effects on both the actor and the critic. Our algorithm builds on Double Q-learning, by taking the minimum value between a pair of critics to limit overestimation. We draw the connection between target networks and overestimation bias, and suggest delaying policy updates to reduce per-update error and further improve performance. We evaluate our method on the suite of OpenAI gym tasks, outperforming the state of the art in every environment tested.

Tasks

Benchmark Results

Reproductions