Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward.
Yanjiang GuoJingyue GaoZheng WuChengming ShiJianyu ChenPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- learning algorithm
- state space
- high dimensional
- temporal difference
- model free
- optimal policy
- action selection
- reward function
- multi agent
- sparse data
- eligibility traces
- total reward
- transfer learning
- markov decision processes
- compressive sensing
- reward shaping
- learning agent
- partially observable environments
- average reward
- policy search
- data sets
- learning problems
- sparse representation
- dynamic programming
- random projections
- multi agent reinforcement learning
- sparse matrix
- temporal difference learning
- sparse coding
- sufficient conditions
- machine learning
- neural network