Support rlintro

[findmyway]

• Removed CumulativeReward.
• Bugfix with MultiAgentHook
• Add VectorSARTTrajectory
• Bugfix with MultiAgentManager
• Add TabularApproximator
• Add VBasedPolicy
• Redefine TabularRandomPolicy

[codecov-io]

Codecov Report

Merging #200 (e2f5a01) into master (ba0c456) will decrease coverage by 0.79%.
The diff coverage is 12.00%.

@@            Coverage Diff             @@
##           master     #200      +/-   ##
==========================================
- Coverage   29.43%   28.63%   -0.80%     
==========================================
  Files          39       41       +2     
  Lines         863      901      +38     
==========================================
+ Hits          254      258       +4     
- Misses        609      643      +34     

Impacted Files	Coverage Δ
src/core/hooks.jl	13.23% <0.00%> (+1.07%)	⬆️
src/policies/agents/agent.jl	0.00% <ø> (ø)
src/policies/agents/multi_agent.jl	0.00% <0.00%> (ø)
src/policies/agents/named_policy.jl	0.00% <0.00%> (ø)
src/policies/agents/trajectories/trajectory.jl	32.25% <0.00%> (-2.23%)	⬇️
...cies/q_based_policies/learners/abstract_learner.jl	0.00% <0.00%> (ø)
src/policies/q_based_policies/q_based_policy.jl	0.00% <0.00%> (ø)
src/policies/random_policy.jl	10.34% <0.00%> (-1.20%)	⬇️
src/policies/tabular_random_policy.jl	0.00% <0.00%> (ø)
src/policies/v_based_policies.jl	0.00% <0.00%> (ø)
... and 4 more

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update ba0c456...e2f5a01. Read the comment docs.