typewriter
typewriter copied to clipboard
logico
An iA Writer inspired color scheme. It has support for vim, vim airline, vim lightline, tmux and urxvt/xterm.
Hey all, I have just cloned the `master` branch to use the commit that fixed the `tensorflow.contrib` errors regarding the `cloud` module. However, when I install it in edit mode...
The contains() call always fails for CompoundActionSpace. This prevents any use of this space for actual reinforcement learning, because Coach often calls contains() to check the values of actions. This...
Hi all, Related the issue that was closed some days ago ( #374 ), the layers output is somewhat confusing when printing the graph. This also extrapolates to the outputs...
Hello, Is it possible to create a Coach Model Zoo with Pretraind RL Networks? Some models like CARLA_DDPG need a huge time to reach a stable stage. or sometimes we...
Following the settings in `rl_coach/presets/Mujoco_PPO.py` and `rl_coach/presets/ControlSuite_DDPG.py`, I'm creating my own presets to run A3C on ControlSuite with the following preset `ControlSuite_A3C.py` file: ``` from rl_coach.agents.actor_critic_agent import ActorCriticAgentParameters from rl_coach.base_parameters...
Hi, I was testing mxnet framework and run Coach with the command: coach -p CartPole_PPO -s 1 --framework mxnet I got the error below, which seems to occur only with...
The estimation of quantile values must be increasing in theory. In practice, it should be ensured by loss function instead of sorting because the quantile regression for a particular transition...
Hello guys, When I try to run MMC algorithm in Ms. Pac-man (graph_manager),after 400 episodes, the training stucks. Initially, I was thinking that maybe the problem was hardware bottleneck, here...
Is there any interface for masking illegal actions? Ideally, I'd like the agent network to only apply the softmax over the set of legal moves (which can be calculated as...
