Towards Combining On-Off-Policy Methods for Real-World Applications
In this paper, we point out a fundamental property of the objective in reinforcement learning, with which we can reformulate the policy gradient objective into a perceptron-like loss function, removing the need to distinguish between on and off policy training. Namely, we posit that it is sufficient to only update a policy $\pi$ for cases that satisfy the condition $A(\frac{\pi}{\mu}-1)\leq0$, where $A$ is the advantage, and $\mu$ is another policy... (read more)
PDFTasks
Datasets
OpenAI Gym
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Sigmoid Activation
Tanh Activation
V-trace
Experience Replay
Entropy Regularization
Residual Connection
Gradient Clipping
RMSProp
ReLU
Max Pooling
Convolution
LSTM
IMPALA
PPO