Shaped Policy Search for Evolutionary Strategies using Waypoints
Not on the map. Why?
Abstract (arXiv)
In this paper, we try to improve exploration in Blackbox methods, particularly Evolution strategies (ES), when applied to Reinforcement Learning (RL) problems where intermediate waypoints/subgoals are available. Since Evolutionary strategies are highly parallelizable, instead of extracting just a scalar cumulative reward, we use the state-action pairs from the trajectories obtained during rollouts/evaluations, to learn the dynamics of the agent. The learnt dynamics are then used in the optimization procedure to speed-up training. Lastly, we show how our proposed approach is universally applicable by presenting results from experiments conducted on Carla driving and UR5 robotic arm simulators.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 15 of its 30 references that are in the map. First posted on arXiv 30 May 2021.
Builds on
15 of 30 references.
References · 15
- 2017Proximal Policy Optimization Algorithmscited by 14,441
- 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
- 2016OpenAI Gymcited by 1,684
- 2017Hindsight Experience Replaycited by 1,096
- 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
- 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 555
- 2016The CMA Evolution Strategy: A Tutorialcited by 364
- 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 352
- 2018Reinforcement Learning from Imperfect Demonstrationscited by 74
- 2019RIDM: Reinforced Inverse Dynamics Modeling for Learning from a Single Observed Demonstrationcited by 19
- 2019Hybrid Reinforcement Learning with Expert State Sequencescited by 14
- 2020robo-gym -- An Open Source Toolkit for Distributed Deep Reinforcement Learning on Real and Simulated Robotscited by 9
3 more
Built on by
Citing papers per year: 2023: 1.
1 paper.