safeRL
safeRL copied to clipboard
hari-sikchi
Safe Reinforcement Learning algorithms
Cleaned up the code and restructured it into an object oriented structure. ## Why? Clutter in `agent2.py` made it almost impossible to debug ## Test: ``` cd $RECOVERYPATH python agent_trainer.py...
## Location: https://github.com/Santara/safeRL/blob/c52382977616075971de68b56e031192e388ce6c/safe_recovery/agent_config.yml#L18-L19 ## Issue: Setting these options to `true` throws the following `Tensorflow reuse error`
In the following line, reward is specified as a list with a single element. https://github.com/hari-sikchi/safeRL/blob/b4f0443b109d5d3290771528115087eb5dd763ce/safe_recovery/agent2.py#L352-L354 For multiple parallel rollouts, this list should be filled up asynchronously by different instances of...