Benchmarking Deep Reinforcement Learning Algorithms for Vision-based Robotics.
Swagat KumarHayden SampsonArdhendu BeheraPublished in: CoRR (2022)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- state space
- markov decision processes
- model free
- reinforcement learning methods
- eligibility traces
- reinforcement learning problems
- temporal difference
- learning algorithm
- dynamic environments
- function approximation
- reward function
- policy search
- prior knowledge
- stochastic games
- partially observable environments
- machine learning
- search space
- search algorithm
- training data